agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 2/6] Refactor index_concurrently_create_copy() for use with REPACK (CONCURRENTLY). 201+ messages / 4 participants [nested] [flat]
* [PATCH 2/6] Refactor index_concurrently_create_copy() for use with REPACK (CONCURRENTLY). @ 2026-01-12 16:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Antonin Houska @ 2026-01-12 16:30 UTC (permalink / raw) This patch moves the code to index_create_copy() and adds a "concurrently" parameter so it can be used by REPACK (CONCURRENTLY). With the CONCURRENTLY option, REPACK cannot simply swap the heap file and rebuild its indexes. Instead, it needs to build a separate set of indexes (including system catalog entries) *before* the actual swap, to reduce the time AccessExclusiveLock needs to be held for. --- src/backend/catalog/index.c | 54 +++++++++++++++++++++++--------- src/backend/commands/indexcmds.c | 6 ++-- src/backend/nodes/makefuncs.c | 9 +++--- src/include/catalog/index.h | 3 ++ src/include/nodes/makefuncs.h | 4 ++- 5 files changed, 54 insertions(+), 22 deletions(-) diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index 5ee6389d39c..f8e6c3d804e 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -1288,15 +1288,32 @@ index_create(Relation heapRelation, /* * index_concurrently_create_copy * - * Create concurrently an index based on the definition of the one provided by - * caller. The index is inserted into catalogs and needs to be built later - * on. This is called during concurrent reindex processing. - * - * "tablespaceOid" is the tablespace to use for this index. + * Variant of index_create_copy(), called during concurrent reindex + * processing. */ Oid index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, Oid tablespaceOid, const char *newName) +{ + return index_create_copy(heapRelation, oldIndexId, tablespaceOid, newName, + true); +} + +/* + * index_create_copy + * + * Create an index based on the definition of the one provided by caller. The + * index is inserted into catalogs. If 'concurrently' is TRUE, it needs to be + * built later on, otherwise it's built immediately. + * + * "tablespaceOid" is the tablespace to use for this index. + * + * The actual implementation of index_concurrently_create_copy(), reusable for + * other purposes. + */ +Oid +index_create_copy(Relation heapRelation, Oid oldIndexId, Oid tablespaceOid, + const char *newName, bool concurrently) { Relation indexRelation; IndexInfo *oldInfo, @@ -1315,6 +1332,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, List *indexColNames = NIL; List *indexExprs = NIL; List *indexPreds = NIL; + int flags = 0; indexRelation = index_open(oldIndexId, RowExclusiveLock); @@ -1325,7 +1343,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, * Concurrent build of an index with exclusion constraints is not * supported. */ - if (oldInfo->ii_ExclusionOps != NULL) + if (oldInfo->ii_ExclusionOps != NULL && concurrently) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), errmsg("concurrent index creation for exclusion constraints is not supported"))); @@ -1381,9 +1399,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, } /* - * Build the index information for the new index. Note that rebuild of - * indexes with exclusion constraints is not supported, hence there is no - * need to fill all the ii_Exclusion* fields. + * Build the index information for the new index. */ newInfo = makeIndexInfo(oldInfo->ii_NumIndexAttrs, oldInfo->ii_NumIndexKeyAttrs, @@ -1392,10 +1408,13 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, indexPreds, oldInfo->ii_Unique, oldInfo->ii_NullsNotDistinct, - false, /* not ready for inserts */ - true, + !concurrently, /* isready */ + concurrently, /* concurrent */ indexRelation->rd_indam->amsummarizing, - oldInfo->ii_WithoutOverlaps); + oldInfo->ii_WithoutOverlaps, + oldInfo->ii_ExclusionOps, + oldInfo->ii_ExclusionProcs, + oldInfo->ii_ExclusionStrats); /* * Extract the list of column names and the column numbers for the new @@ -1433,6 +1452,9 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, stattargets[i].isnull = isnull; } + if (concurrently) + flags = INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT; + /* * Now create the new index. * @@ -1456,7 +1478,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, indcoloptions->values, stattargets, reloptionsDatum, - INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT, + flags, 0, true, /* allow table to be a system catalog? */ false, /* is_internal? */ @@ -2450,7 +2472,8 @@ BuildIndexInfo(Relation index) indexStruct->indisready, false, index->rd_indam->amsummarizing, - indexStruct->indisexclusion && indexStruct->indisunique); + indexStruct->indisexclusion && indexStruct->indisunique, + NULL, NULL, NULL); /* fill in attribute numbers */ for (i = 0; i < numAtts; i++) @@ -2510,7 +2533,8 @@ BuildDummyIndexInfo(Relation index) indexStruct->indisready, false, index->rd_indam->amsummarizing, - indexStruct->indisexclusion && indexStruct->indisunique); + indexStruct->indisexclusion && indexStruct->indisunique, + NULL, NULL, NULL); /* fill in attribute numbers */ for (i = 0; i < numAtts; i++) diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c index 635679cc1f2..34209bd1393 100644 --- a/src/backend/commands/indexcmds.c +++ b/src/backend/commands/indexcmds.c @@ -243,7 +243,8 @@ CheckIndexCompatible(Oid oldId, */ indexInfo = makeIndexInfo(numberOfAttributes, numberOfAttributes, accessMethodId, NIL, NIL, false, false, - false, false, amsummarizing, isWithoutOverlaps); + false, false, amsummarizing, isWithoutOverlaps, + NULL, NULL, NULL); typeIds = palloc_array(Oid, numberOfAttributes); collationIds = palloc_array(Oid, numberOfAttributes); opclassIds = palloc_array(Oid, numberOfAttributes); @@ -930,7 +931,8 @@ DefineIndex(ParseState *pstate, !concurrent, concurrent, amissummarizing, - stmt->iswithoutoverlaps); + stmt->iswithoutoverlaps, + NULL, NULL, NULL); typeIds = palloc_array(Oid, numberOfAttributes); collationIds = palloc_array(Oid, numberOfAttributes); diff --git a/src/backend/nodes/makefuncs.c b/src/backend/nodes/makefuncs.c index 2caec621d73..ca7e21e8349 100644 --- a/src/backend/nodes/makefuncs.c +++ b/src/backend/nodes/makefuncs.c @@ -834,7 +834,8 @@ IndexInfo * makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions, List *predicates, bool unique, bool nulls_not_distinct, bool isready, bool concurrent, bool summarizing, - bool withoutoverlaps) + bool withoutoverlaps, Oid *exclusion_ops, Oid *exclusion_procs, + uint16 *exclusion_strats) { IndexInfo *n = makeNode(IndexInfo); @@ -863,9 +864,9 @@ makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions, n->ii_PredicateState = NULL; /* exclusion constraints */ - n->ii_ExclusionOps = NULL; - n->ii_ExclusionProcs = NULL; - n->ii_ExclusionStrats = NULL; + n->ii_ExclusionOps = exclusion_ops; + n->ii_ExclusionProcs = exclusion_procs; + n->ii_ExclusionStrats = exclusion_strats; /* speculative inserts */ n->ii_UniqueOps = NULL; diff --git a/src/include/catalog/index.h b/src/include/catalog/index.h index b259c4141ed..3426087b445 100644 --- a/src/include/catalog/index.h +++ b/src/include/catalog/index.h @@ -99,6 +99,9 @@ extern Oid index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId, Oid tablespaceOid, const char *newName); +extern Oid index_create_copy(Relation heapRelation, Oid oldIndexId, + Oid tablespaceOid, const char *newName, + bool concurrently); extern void index_concurrently_build(Oid heapRelationId, Oid indexRelationId); diff --git a/src/include/nodes/makefuncs.h b/src/include/nodes/makefuncs.h index 982ec25ae14..dcea148ae1a 100644 --- a/src/include/nodes/makefuncs.h +++ b/src/include/nodes/makefuncs.h @@ -99,7 +99,9 @@ extern IndexInfo *makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions, List *predicates, bool unique, bool nulls_not_distinct, bool isready, bool concurrent, - bool summarizing, bool withoutoverlaps); + bool summarizing, bool withoutoverlaps, + Oid *exclusion_ops, Oid *exclusion_procs, + uint16 *exclusion_strats); extern Node *makeStringConst(char *str, int location); extern DefElem *makeDefElem(char *name, Node *arg, int location); -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v30-0003-Move-conversion-of-a-historic-to-MVCC-snapshot-to-a-.patch ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-05-29 12:35 Samba Siva <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw) - Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling. - Updated analyze.c to utilize the hook if registered. - Added tests to ensure ANALYZE completes without errors with the new hook. --- doc/src/sgml/xfunc.sgml | 10 ++++++++++ src/backend/commands/analyze.c | 24 ++++++++++++++++++++---- src/include/commands/vacuum.h | 11 +++++++++++ src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++ src/test/regress/parallel_schedule | 1 + src/test/regress/sql/analyze.sql | 24 ++++++++++++++++++++++++ 6 files changed, 86 insertions(+), 4 deletions(-) create mode 100644 src/test/regress/expected/analyze.out create mode 100644 src/test/regress/sql/analyze.sql diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml index 1eb5abffd8..f1ef025ae2 100644 --- a/doc/src/sgml/xfunc.sgml +++ b/doc/src/sgml/xfunc.sgml @@ -4203,4 +4203,14 @@ supportfn(internal) returns internal To create such conditions, the support function must implement the <literal>SupportRequestIndexCondition</literal> request type. </para> + + <para> + The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions + to override the row sampling function during <command>ANALYZE</command> for regular + heap relations. This is useful for extensions/systems which implement distributed + databases and want to sample rows from remote nodes instead of the local heap. + The hook function fills the provided <literal>rows[]</literal> buffer with at most + <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the + estimated total live row count of the relation. + </para> </sect1> diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 4fffb76e55..3560acdff1 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -74,6 +74,8 @@ int default_statistics_target = 100; static MemoryContext anl_context = NULL; static BufferAccessStrategy vac_strategy; +/* Hook for plugins to acquire sample rows for ANALYZE */ +AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL; static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, @@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation, if (onerel->rd_rel->relkind == RELKIND_RELATION || onerel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so we'll use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so we'll use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; /* Also get regular table's size */ relpages = RelationGetNumberOfBlocks(onerel); } @@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, if (childrel->rd_rel->relkind == RELKIND_RELATION || childrel->rd_rel->relkind == RELKIND_MATVIEW) { - /* Regular table, so use the regular row acquisition function */ - acquirefunc = acquire_sample_rows; + /* + * Regular table, so use the regular row acquisition function. + * If a plugin has registered a hook to acquire sample rows, use it; + * otherwise use the default function. + */ + if (AcquireSampleRowsFunc_hook) + acquirefunc = AcquireSampleRowsFunc_hook; + else + acquirefunc = acquire_sample_rows; relpages = RelationGetNumberOfBlocks(childrel); } else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index bc37a80dc7..146f936861 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -21,6 +21,7 @@ #include "catalog/pg_class.h" #include "catalog/pg_statistic.h" #include "catalog/pg_type.h" +#include "foreign/fdwapi.h" #include "parser/parse_node.h" #include "storage/buf.h" #include "storage/lock.h" @@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats, int samplerows, double totalrows); +/* Hook type for plugins to acquire sample rows for ANALYZE */ +typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type; + typedef struct VacAttrStats { /* @@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit; extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns; +/* + * Hook for plugins to override row sampling during ANALYZE. + * Also applies to child relations of partitioned/inherited tables. + * See acquire_sample_rows() in src/backend/commands/analyze.c. + */ +extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook; + /* in commands/vacuum.c */ extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel); extern void vacuum(List *relations, VacuumParams *params, diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 0000000000..5bb6bbc45b --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1,20 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; +-- Should complete without error +ANALYZE employees; +DROP TABLE employees; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e1e0c54019..71978ef858 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -94,6 +94,7 @@ test: vacuum_parallel # Run this alone, because concurrent DROP TABLE would make non-superuser # "ANALYZE;" fail with "relation with OID $n does not exist". test: maintain_every +test: analyze # no relation related tests can be put in this group test: publication subscription diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 0000000000..e0bc84e9f9 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1,24 @@ +-- Test AcquireSampleRowsFunc_hook +-- Usually this would be tested via a C extension. +-- Here we just confirm this does not break the existing ANALYZE code +-- by verifying that ANALYZE completes without error. + +CREATE TABLE employees ( + id SERIAL PRIMARY KEY, + name TEXT, + department TEXT, + salary NUMERIC +); + +INSERT INTO employees + SELECT + i, + 'Employee ' || i, + 'Department ' || (i % 5), + (i % 100) * 1000 + 50000 + FROM generate_series(1, 1000) i; + +-- Should complete without error +ANALYZE employees; + +DROP TABLE employees; -- 2.50.1 (Apple Git-155) ------=_Part_741589_445982825.1782438414800-- ^ permalink raw reply [nested|flat] 201+ messages in thread
* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-06-26 01:46 Samba Siva Reddy Chinta <[email protected]> 0 siblings, 1 reply; 201+ messages in thread From: Samba Siva Reddy Chinta @ 2026-06-26 01:46 UTC (permalink / raw) To: pgsql-hackers <[email protected]> Hi all, Attached is a patch that adds a hook, AcquireSampleRowsFunc_hook, allowing extensions to override the row sampling function used during ANALYZE for regular heap relations. Motivation Extensions that implement horizontal scaling of tables currently have no clean way to participate in ANALYZE's row sampling. The default acquire_sample_rows() only knows how to sample the local heap, so a distributed-table extension wanting accurate statistics has to either: maintain its own separate stats-collection machinery outside of ANALYZE entirely, or duplicate/reimplement parts of analyze.c's sampling logic to pull rows from remote nodes. This hook lets such an extension plug into the existing ANALYZE code path and supply its own row acquisition function, without having to reinvent stats collection or duplicate logic that already exists in core. What the patch does Adds AcquireSampleRowsFunc_hook (typed identically to AcquireSampleRowsFunc) in vacuum.h. In analyze.c, both analyze_rel() and acquire_inherited_sample_rows() check the hook and use it in place of acquire_sample_rows() when set. Adds doc text in xfunc.sgml describing the hook's contract (fill rows[] up to targrows, set *totalrows). Adds a regression test confirming ANALYZE still completes normally with the hook unset (the hook itself needs a C extension to exercise meaningfully, so this just guards against regressions in the unset case). ​Regards, Samba Siva Reddy http://sambasivareddy.in ^ permalink raw reply [nested|flat] 201+ messages in thread
* Re: [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-06-26 12:41 Ashutosh Bapat <[email protected]> parent: Samba Siva Reddy Chinta <[email protected]> 0 siblings, 1 reply; 201+ messages in thread From: Ashutosh Bapat @ 2026-06-26 12:41 UTC (permalink / raw) To: Samba Siva Reddy Chinta <[email protected]>; +Cc: pgsql-hackers <[email protected]> Hi Samba Siva, On Fri, Jun 26, 2026 at 7:17 AM Samba Siva Reddy Chinta <[email protected]> wrote: > > Hi all, > > Attached is a patch that adds a hook, AcquireSampleRowsFunc_hook, allowing extensions to override the row sampling function used during ANALYZE for regular heap relations. > > Motivation > > Extensions that implement horizontal scaling of tables currently have no clean way to participate in ANALYZE's row sampling. The default acquire_sample_rows() only knows how to sample the local heap, so a distributed-table extension wanting accurate statistics has to either: > > maintain its own separate stats-collection machinery outside of ANALYZE entirely, or > duplicate/reimplement parts of analyze.c's sampling logic to pull rows from remote nodes. > > This hook lets such an extension plug into the existing ANALYZE code path and supply its own row acquisition function, without having to reinvent stats collection or duplicate logic that already exists in core. > > What the patch does > > Adds AcquireSampleRowsFunc_hook (typed identically to AcquireSampleRowsFunc) in vacuum.h. > In analyze.c, both analyze_rel() and acquire_inherited_sample_rows() check the hook and use it in place of acquire_sample_rows() when set. > Adds doc text in xfunc.sgml describing the hook's contract (fill rows[] up to targrows, set *totalrows). > Adds a regression test confirming ANALYZE still completes normally with the hook unset (the hook itself needs a C extension to exercise meaningfully, so this just guards against regressions in the unset case). > If you have implemented sharding using inheritance or partitioning and FDW, the facility to fetch statistics of foreign tables from foreign server can be useful here. IIUC, there is a limitation on using it for inherited foreign tables, but it's worth exploring and improving for your usecase. -- Best Wishes, Ashutosh Bapat ^ permalink raw reply [nested|flat] 201+ messages in thread
* Re: [PATCH] Add hook for plugins to acquire sample rows during ANALYZE @ 2026-07-05 02:22 Samba Siva Reddy Chinta <[email protected]> parent: Ashutosh Bapat <[email protected]> 0 siblings, 0 replies; 201+ messages in thread From: Samba Siva Reddy Chinta @ 2026-07-05 02:22 UTC (permalink / raw) To: Ashutosh Bapat <[email protected]>; +Cc: pgsql-hackers <[email protected]> Hi Ashutosh, If you have implemented sharding using inheritance or partitioning and FDW, the facility to fetch statistics of foreign tables from foreign server can be useful here. IIUC, there is a limitation on using it for inherited foreign tables, but it's worth exploring and improving for your usecase. Thanks for the suggestion. To clarify, this is not FDW-based sharding. The shards here are plain PostgreSQL tables distributed across the nodes like Citus, when a table is distributed, the base table remains on the coordinator and its shards spread across the workers as regular PostgreSQL heap tables. Since there are no foreign tables involved, the FDW stats-fetching mechanism does not apply here. The base table holds no actual row data, but the shards as the real data - which is precisely the gap AcquireSampleRowsFunc_hook is meant to address. Happy to clarify further if needed. Thanks, Samba Siva Reddy From: Ashutosh Bapat <[email protected]> To: "Samba Siva Reddy Chinta"<[email protected]> Cc: "pgsql-hackers"<[email protected]> Date: Fri, 26 Jun 2026 18:11:50 +0530 Subject: Re: [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Hi Samba Siva, On Fri, Jun 26, 2026 at 7:17 AM Samba Siva Reddy Chinta < mailto:[email protected] > wrote: > > Hi all, > > Attached is a patch that adds a hook, AcquireSampleRowsFunc_hook, allowing extensions to override the row sampling function used during ANALYZE for regular heap relations. > > Motivation > > Extensions that implement horizontal scaling of tables currently have no clean way to participate in ANALYZE's row sampling. The default acquire_sample_rows() only knows how to sample the local heap, so a distributed-table extension wanting accurate statistics has to either: > > maintain its own separate stats-collection machinery outside of ANALYZE entirely, or > duplicate/reimplement parts of analyze.c's sampling logic to pull rows from remote nodes. > > This hook lets such an extension plug into the existing ANALYZE code path and supply its own row acquisition function, without having to reinvent stats collection or duplicate logic that already exists in core. > > What the patch does > > Adds AcquireSampleRowsFunc_hook (typed identically to AcquireSampleRowsFunc) in vacuum.h. > In analyze.c, both analyze_rel() and acquire_inherited_sample_rows() check the hook and use it in place of acquire_sample_rows() when set. > Adds doc text in xfunc.sgml describing the hook's contract (fill rows[] up to targrows, set *totalrows). > Adds a regression test confirming ANALYZE still completes normally with the hook unset (the hook itself needs a C extension to exercise meaningfully, so this just guards against regressions in the unset case). > If you have implemented sharding using inheritance or partitioning and FDW, the facility to fetch statistics of foreign tables from foreign server can be useful here. IIUC, there is a limitation on using it for inherited foreign tables, but it's worth exploring and improving for your usecase. -- Best Wishes, Ashutosh Bapat Regards, Samba Siva Reddy http://sambasivareddy.in ^ permalink raw reply [nested|flat] 201+ messages in thread
end of thread, other threads:[~2026-07-05 02:22 UTC | newest] Thread overview: 201+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2026-01-12 16:30 [PATCH 2/6] Refactor index_concurrently_create_copy() for use with REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-05-29 12:35 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva <[email protected]> 2026-06-26 01:46 [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva Reddy Chinta <[email protected]> 2026-06-26 12:41 ` Re: [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Ashutosh Bapat <[email protected]> 2026-07-05 02:22 ` Re: [PATCH] Add hook for plugins to acquire sample rows during ANALYZE Samba Siva Reddy Chinta <[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