agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v2] Provide relfilenode statistics
71+ messages / 4 participants
[nested] [flat]

* [PATCH v2] Provide relfilenode statistics
@ 2023-11-16 02:30  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 71+ messages in thread

From: Bertrand Drouvot @ 2023-11-16 02:30 UTC (permalink / raw)

We currently don’t have writes counters for relations.
The reason is that we don’t have the relation OID when writing buffers out.
Tracking writes per relfilenode would allow us to track/consolidate writes per
relation.

relfilenode stats is also beneficial for the "Split index and table statistics
into different types of stats" work in progress: it would allow us to avoid
additional branches in some situations.

=== Remarks ===

This is a POC patch. There is still work to do: there is more places we should
add relfilenode counters, create more APIS to retrieve the relfilenode stats,
the patch takes care of rewrite generated by TRUNCATE but there is more to
care about like CLUSTER,VACUUM FULL.

The new logic to retrieve stats in pg_statio_all_tables has been implemented
only for the new blocks_written stat (we'd need to do the same for the existing
buffer read / buffer hit if we agree on the approach implemented here).

The goal of this patch is to start the discussion and agree on the design before
moving forward.
---
 src/backend/access/rmgrdesc/xactdesc.c        |   5 +-
 src/backend/catalog/storage.c                 |   8 ++
 src/backend/catalog/system_functions.sql      |   2 +-
 src/backend/catalog/system_views.sql          |   5 +-
 src/backend/postmaster/checkpointer.c         |   5 +
 src/backend/storage/buffer/bufmgr.c           |   6 +-
 src/backend/storage/smgr/md.c                 |   7 ++
 src/backend/utils/activity/pgstat.c           |  39 ++++--
 src/backend/utils/activity/pgstat_database.c  |  12 +-
 src/backend/utils/activity/pgstat_function.c  |  13 +-
 src/backend/utils/activity/pgstat_relation.c  | 112 ++++++++++++++++--
 src/backend/utils/activity/pgstat_replslot.c  |  13 +-
 src/backend/utils/activity/pgstat_shmem.c     |  19 ++-
 .../utils/activity/pgstat_subscription.c      |  12 +-
 src/backend/utils/activity/pgstat_xact.c      |  60 +++++++---
 src/backend/utils/adt/pgstatfuncs.c           |  34 +++++-
 src/include/access/tableam.h                  |  19 +++
 src/include/access/xact.h                     |   1 +
 src/include/catalog/pg_proc.dat               |  14 ++-
 src/include/pgstat.h                          |  19 ++-
 src/include/utils/pgstat_internal.h           |  34 ++++--
 src/test/recovery/t/029_stats_restart.pl      |  40 +++----
 .../recovery/t/030_stats_cleanup_replica.pl   |   6 +-
 src/test/regress/expected/rules.out           |  12 +-
 src/test/regress/expected/stats.out           |  30 ++---
 src/test/regress/sql/stats.sql                |  30 ++---
 src/test/subscription/t/026_stats.pl          |   4 +-
 src/tools/pgindent/typedefs.list              |   1 +
 28 files changed, 415 insertions(+), 147 deletions(-)
   4.6% src/backend/catalog/
  47.8% src/backend/utils/activity/
   6.5% src/backend/utils/adt/
   3.7% src/backend/
   3.3% src/include/access/
   3.3% src/include/catalog/
   6.2% src/include/utils/
   3.3% src/include/
  12.1% src/test/recovery/t/
   5.5% src/test/regress/expected/
   3.0% src/test/

diff --git a/src/backend/access/rmgrdesc/xactdesc.c b/src/backend/access/rmgrdesc/xactdesc.c
index dccca201e0..c02b079645 100644
--- a/src/backend/access/rmgrdesc/xactdesc.c
+++ b/src/backend/access/rmgrdesc/xactdesc.c
@@ -319,10 +319,11 @@ xact_desc_stats(StringInfo buf, const char *label,
 		appendStringInfo(buf, "; %sdropped stats:", label);
 		for (i = 0; i < ndropped; i++)
 		{
-			appendStringInfo(buf, " %d/%u/%u",
+			appendStringInfo(buf, " %d/%u/%u/%u",
 							 dropped_stats[i].kind,
 							 dropped_stats[i].dboid,
-							 dropped_stats[i].objoid);
+							 dropped_stats[i].objoid,
+							 dropped_stats[i].relfile);
 		}
 	}
 }
diff --git a/src/backend/catalog/storage.c b/src/backend/catalog/storage.c
index f56b3cc0f2..db6107cd90 100644
--- a/src/backend/catalog/storage.c
+++ b/src/backend/catalog/storage.c
@@ -33,6 +33,7 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/rel.h"
 
 /* GUC variables */
@@ -152,6 +153,7 @@ RelationCreateStorage(RelFileLocator rlocator, char relpersistence,
 	if (needs_wal)
 		log_smgrcreate(&srel->smgr_rlocator.locator, MAIN_FORKNUM);
 
+	pgstat_create_transactional(PGSTAT_KIND_RELFILENODE, rlocator.dbOid, rlocator.spcOid, rlocator.relNumber);
 	/*
 	 * Add the relation to the list of stuff to delete at abort, if we are
 	 * asked to do so.
@@ -227,6 +229,8 @@ RelationDropStorage(Relation rel)
 	 * for now I'll keep the logic simple.
 	 */
 
+	pgstat_drop_transactional(PGSTAT_KIND_RELFILENODE, rel->rd_locator.dbOid, rel->rd_locator.spcOid,  rel->rd_locator.relNumber);
+
 	RelationCloseSmgr(rel);
 }
 
@@ -253,6 +257,9 @@ RelationPreserveStorage(RelFileLocator rlocator, bool atCommit)
 	PendingRelDelete *pending;
 	PendingRelDelete *prev;
 	PendingRelDelete *next;
+	PgStat_SubXactStatus *xact_state;
+
+	xact_state = pgStatXactStack;
 
 	prev = NULL;
 	for (pending = pendingDeletes; pending != NULL; pending = next)
@@ -267,6 +274,7 @@ RelationPreserveStorage(RelFileLocator rlocator, bool atCommit)
 			else
 				pendingDeletes = next;
 			pfree(pending);
+			PgStat_RemoveRelFileNodeFromDroppedStats(xact_state, rlocator);
 			/* prev does not change */
 		}
 		else
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index ae099e328c..140c8d556c 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -681,7 +681,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM publ
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
-REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, oid) FROM public;
+REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, oid, oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_subscription_stats(oid) FROM public;
 
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 53047cab5f..b0d7af6df0 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -750,6 +750,7 @@ CREATE VIEW pg_statio_all_tables AS
             C.relname AS relname,
             pg_stat_get_blocks_fetched(C.oid) -
                     pg_stat_get_blocks_hit(C.oid) AS heap_blks_read,
+			pg_stat_get_blocks_written(C.oid) + pg_stat_get_relfilenode_blocks_written(d.oid, CASE WHEN C.reltablespace <> 0 THEN C.reltablespace ELSE d.dattablespace END, C.relfilenode) AS heap_blks_written,
             pg_stat_get_blocks_hit(C.oid) AS heap_blks_hit,
             I.idx_blks_read AS idx_blks_read,
             I.idx_blks_hit AS idx_blks_hit,
@@ -758,7 +759,7 @@ CREATE VIEW pg_statio_all_tables AS
             pg_stat_get_blocks_hit(T.oid) AS toast_blks_hit,
             X.idx_blks_read AS tidx_blks_read,
             X.idx_blks_hit AS tidx_blks_hit
-    FROM pg_class C LEFT JOIN
+    FROM pg_database d, pg_class C LEFT JOIN
             pg_class T ON C.reltoastrelid = T.oid
             LEFT JOIN pg_namespace N ON (N.oid = C.relnamespace)
             LEFT JOIN LATERAL (
@@ -775,7 +776,7 @@ CREATE VIEW pg_statio_all_tables AS
                      sum(pg_stat_get_blocks_hit(indexrelid))::bigint
                      AS idx_blks_hit
               FROM pg_index WHERE indrelid = T.oid ) X ON true
-    WHERE C.relkind IN ('r', 't', 'm');
+    WHERE C.relkind IN ('r', 't', 'm') AND d.datname = current_database();
 
 CREATE VIEW pg_statio_sys_tables AS
     SELECT * FROM pg_statio_all_tables
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index 3c68a9904d..0ff2812218 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -519,6 +519,11 @@ CheckpointerMain(char *startup_data, size_t startup_data_len)
 		/* Report pending statistics to the cumulative stats system */
 		pgstat_report_checkpointer();
 		pgstat_report_wal(true);
+		/*
+		 *  No need to check for transaction state in checkpointer before
+		 *  calling pgstat_report_stat().
+		 */
+		pgstat_report_stat(true);
 
 		/*
 		 * If any checkpoint flags have been set, redo the loop to handle the
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 49637284f9..06d89ba26b 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -1121,9 +1121,9 @@ PinBufferForBlock(Relation rel,
 		 * WaitReadBuffers() (so, not for hits, and not for buffers that are
 		 * zeroed instead), the per-relation stats always count them.
 		 */
-		pgstat_count_buffer_read(rel);
+		pgstat_report_relfilenode_buffer_read(rel);
 		if (*foundPtr)
-			pgstat_count_buffer_hit(rel);
+			pgstat_report_relfilenode_buffer_hit(rel);
 	}
 	if (*foundPtr)
 	{
@@ -3838,6 +3838,8 @@ FlushBuffer(BufferDesc *buf, SMgrRelation reln, IOObject io_object,
 
 	pgBufferUsage.shared_blks_written++;
 
+	pgstat_report_relfilenode_blks_written(reln->smgr_rlocator.locator);
+
 	/*
 	 * Mark the buffer as clean (unless BM_JUST_DIRTIED has become set) and
 	 * end the BM_IO_IN_PROGRESS state.
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 6796756358..5bc5fc65cd 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -1447,12 +1447,16 @@ DropRelationFiles(RelFileLocator *delrels, int ndelrels, bool isRedo)
 {
 	SMgrRelation *srels;
 	int			i;
+	int         not_freed_count = 0;
 
 	srels = palloc(sizeof(SMgrRelation) * ndelrels);
 	for (i = 0; i < ndelrels; i++)
 	{
 		SMgrRelation srel = smgropen(delrels[i], INVALID_PROC_NUMBER);
 
+		if (!pgstat_drop_entry(PGSTAT_KIND_RELFILENODE, delrels[i].dbOid, delrels[i].spcOid, delrels[i].relNumber))
+			not_freed_count++;
+
 		if (isRedo)
 		{
 			ForkNumber	fork;
@@ -1463,6 +1467,9 @@ DropRelationFiles(RelFileLocator *delrels, int ndelrels, bool isRedo)
 		srels[i] = srel;
 	}
 
+	if (not_freed_count > 0)
+		pgstat_request_entry_refs_gc();
+
 	smgrdounlinkall(srels, ndelrels, isRedo);
 
 	for (i = 0; i < ndelrels; i++)
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index dcc2ad8d95..e3b6f45828 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -288,6 +288,19 @@ static const PgStat_KindInfo pgstat_kind_infos[PGSTAT_NUM_KINDS] = {
 		.delete_pending_cb = pgstat_relation_delete_pending_cb,
 	},
 
+	[PGSTAT_KIND_RELFILENODE] = {
+		.name = "relfilenode",
+
+		.fixed_amount = false,
+
+		.shared_size = sizeof(PgStatShared_RelFileNode),
+		.shared_data_off = offsetof(PgStatShared_RelFileNode, stats),
+		.shared_data_len = sizeof(((PgStatShared_RelFileNode *) 0)->stats),
+		.pending_size = sizeof(PgStat_StatRelFileNodeEntry),
+
+		.flush_pending_cb = pgstat_relfilenode_flush_cb,
+	},
+
 	[PGSTAT_KIND_FUNCTION] = {
 		.name = "function",
 
@@ -651,7 +664,7 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush database / relation / function / ... stats */
+	/* flush database / relation / function / relfilenode / ... stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
 	/* flush IO stats */
@@ -731,7 +744,7 @@ pgstat_reset_counters(void)
  * GRANT system.
  */
 void
-pgstat_reset(PgStat_Kind kind, Oid dboid, Oid objoid)
+pgstat_reset(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile)
 {
 	const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 	TimestampTz ts = GetCurrentTimestamp();
@@ -740,7 +753,7 @@ pgstat_reset(PgStat_Kind kind, Oid dboid, Oid objoid)
 	Assert(!pgstat_get_kind_info(kind)->fixed_amount);
 
 	/* reset the "single counter" */
-	pgstat_reset_entry(kind, dboid, objoid, ts);
+	pgstat_reset_entry(kind, dboid, objoid, relfile, ts);
 
 	if (!kind_info->accessed_across_databases)
 		pgstat_reset_database_timestamp(dboid, ts);
@@ -809,7 +822,7 @@ pgstat_clear_snapshot(void)
 }
 
 void *
-pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, Oid objoid)
+pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile)
 {
 	PgStat_HashKey key;
 	PgStat_EntryRef *entry_ref;
@@ -825,6 +838,7 @@ pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, Oid objoid)
 	key.kind = kind;
 	key.dboid = dboid;
 	key.objoid = objoid;
+	key.relfile = relfile;
 
 	/* if we need to build a full snapshot, do so */
 	if (pgstat_fetch_consistency == PGSTAT_FETCH_CONSISTENCY_SNAPSHOT)
@@ -850,7 +864,7 @@ pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, Oid objoid)
 
 	pgStatLocal.snapshot.mode = pgstat_fetch_consistency;
 
-	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, false, NULL);
+	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, relfile, false, NULL);
 
 	if (entry_ref == NULL || entry_ref->shared_entry->dropped)
 	{
@@ -919,13 +933,13 @@ pgstat_get_stat_snapshot_timestamp(bool *have_snapshot)
 }
 
 bool
-pgstat_have_entry(PgStat_Kind kind, Oid dboid, Oid objoid)
+pgstat_have_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile)
 {
 	/* fixed-numbered stats always exist */
 	if (pgstat_get_kind_info(kind)->fixed_amount)
 		return true;
 
-	return pgstat_get_entry_ref(kind, dboid, objoid, false, NULL) != NULL;
+	return pgstat_get_entry_ref(kind, dboid, objoid, relfile, false, NULL) != NULL;
 }
 
 /*
@@ -1102,7 +1116,8 @@ pgstat_build_snapshot_fixed(PgStat_Kind kind)
  * created, false otherwise.
  */
 PgStat_EntryRef *
-pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid, bool *created_entry)
+pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid,
+						  RelFileNumber relfile, bool *created_entry)
 {
 	PgStat_EntryRef *entry_ref;
 
@@ -1117,7 +1132,7 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid, bool *created
 								  ALLOCSET_SMALL_SIZES);
 	}
 
-	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid,
+	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, relfile,
 									 true, created_entry);
 
 	if (entry_ref->pending == NULL)
@@ -1140,11 +1155,11 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid, bool *created
  * that it shouldn't be needed.
  */
 PgStat_EntryRef *
-pgstat_fetch_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid)
+pgstat_fetch_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile)
 {
 	PgStat_EntryRef *entry_ref;
 
-	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, false, NULL);
+	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, relfile, false, NULL);
 
 	if (entry_ref == NULL || entry_ref->pending == NULL)
 		return NULL;
@@ -1173,7 +1188,7 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 }
 
 /*
- * Flush out pending stats for database objects (databases, relations,
+ * Flush out pending stats for database objects (databases, relations, relfilenodes,
  * functions).
  */
 static bool
diff --git a/src/backend/utils/activity/pgstat_database.c b/src/backend/utils/activity/pgstat_database.c
index 29bc090974..cf77f2dbdb 100644
--- a/src/backend/utils/activity/pgstat_database.c
+++ b/src/backend/utils/activity/pgstat_database.c
@@ -43,7 +43,7 @@ static PgStat_Counter pgLastSessionReportTime = 0;
 void
 pgstat_drop_database(Oid databaseid)
 {
-	pgstat_drop_transactional(PGSTAT_KIND_DATABASE, databaseid, InvalidOid);
+	pgstat_drop_transactional(PGSTAT_KIND_DATABASE, databaseid, InvalidOid, InvalidOid);
 }
 
 /*
@@ -66,7 +66,7 @@ pgstat_report_autovac(Oid dboid)
 	 * operation so it doesn't matter if we get blocked here a little.
 	 */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_DATABASE,
-											dboid, InvalidOid, false);
+											dboid, InvalidOid, InvalidOid, false);
 
 	dbentry = (PgStatShared_Database *) entry_ref->shared_stats;
 	dbentry->stats.last_autovac_time = GetCurrentTimestamp();
@@ -150,7 +150,7 @@ pgstat_report_checksum_failures_in_db(Oid dboid, int failurecount)
 	 * common enough for that to be a problem.
 	 */
 	entry_ref =
-		pgstat_get_entry_ref_locked(PGSTAT_KIND_DATABASE, dboid, InvalidOid, false);
+		pgstat_get_entry_ref_locked(PGSTAT_KIND_DATABASE, dboid, InvalidOid, InvalidOid, false);
 
 	sharedent = (PgStatShared_Database *) entry_ref->shared_stats;
 	sharedent->stats.checksum_failures += failurecount;
@@ -242,7 +242,7 @@ PgStat_StatDBEntry *
 pgstat_fetch_stat_dbentry(Oid dboid)
 {
 	return (PgStat_StatDBEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_DATABASE, dboid, InvalidOid);
+		pgstat_fetch_entry(PGSTAT_KIND_DATABASE, dboid, InvalidOid, InvalidOid);
 }
 
 void
@@ -341,7 +341,7 @@ pgstat_prep_database_pending(Oid dboid)
 	Assert(!OidIsValid(dboid) || OidIsValid(MyDatabaseId));
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_DATABASE, dboid, InvalidOid,
-										  NULL);
+										  InvalidOid, NULL);
 
 	return entry_ref->pending;
 }
@@ -357,7 +357,7 @@ pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts)
 	PgStatShared_Database *dbentry;
 
 	dbref = pgstat_get_entry_ref_locked(PGSTAT_KIND_DATABASE, MyDatabaseId, InvalidOid,
-										false);
+										InvalidOid, false);
 
 	dbentry = (PgStatShared_Database *) dbref->shared_stats;
 	dbentry->stats.stat_reset_timestamp = ts;
diff --git a/src/backend/utils/activity/pgstat_function.c b/src/backend/utils/activity/pgstat_function.c
index d26da551a4..440e44e300 100644
--- a/src/backend/utils/activity/pgstat_function.c
+++ b/src/backend/utils/activity/pgstat_function.c
@@ -46,7 +46,8 @@ pgstat_create_function(Oid proid)
 {
 	pgstat_create_transactional(PGSTAT_KIND_FUNCTION,
 								MyDatabaseId,
-								proid);
+								proid,
+								InvalidOid);
 }
 
 /*
@@ -61,7 +62,8 @@ pgstat_drop_function(Oid proid)
 {
 	pgstat_drop_transactional(PGSTAT_KIND_FUNCTION,
 							  MyDatabaseId,
-							  proid);
+							  proid,
+							  InvalidOid);
 }
 
 /*
@@ -86,6 +88,7 @@ pgstat_init_function_usage(FunctionCallInfo fcinfo,
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_FUNCTION,
 										  MyDatabaseId,
 										  fcinfo->flinfo->fn_oid,
+										  InvalidOid,
 										  &created_entry);
 
 	/*
@@ -113,7 +116,7 @@ pgstat_init_function_usage(FunctionCallInfo fcinfo,
 		if (!SearchSysCacheExists1(PROCOID, ObjectIdGetDatum(fcinfo->flinfo->fn_oid)))
 		{
 			pgstat_drop_entry(PGSTAT_KIND_FUNCTION, MyDatabaseId,
-							  fcinfo->flinfo->fn_oid);
+							  fcinfo->flinfo->fn_oid, InvalidOid);
 			ereport(ERROR, errcode(ERRCODE_UNDEFINED_FUNCTION),
 					errmsg("function call to dropped function"));
 		}
@@ -224,7 +227,7 @@ find_funcstat_entry(Oid func_id)
 {
 	PgStat_EntryRef *entry_ref;
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_FUNCTION, MyDatabaseId, func_id);
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_FUNCTION, MyDatabaseId, func_id, InvalidOid);
 
 	if (entry_ref)
 		return entry_ref->pending;
@@ -239,5 +242,5 @@ PgStat_StatFuncEntry *
 pgstat_fetch_stat_funcentry(Oid func_id)
 {
 	return (PgStat_StatFuncEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_FUNCTION, MyDatabaseId, func_id);
+		pgstat_fetch_entry(PGSTAT_KIND_FUNCTION, MyDatabaseId, func_id, InvalidOid);
 }
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 8a3f7d434c..136dd6c85b 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -44,6 +44,7 @@ typedef struct TwoPhasePgStatRecord
 
 
 static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+PgStat_StatRelFileNodeEntry *pgstat_prep_relfilenode_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -69,6 +70,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	dst_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
 										  dst->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
 										  RelationGetRelid(dst),
+										  InvalidOid,
 										  false);
 
 	dstshstats = (PgStatShared_Relation *) dst_ref->shared_stats;
@@ -170,7 +172,7 @@ pgstat_create_relation(Relation rel)
 {
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
 								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								RelationGetRelid(rel), InvalidOid);
 }
 
 /*
@@ -184,7 +186,7 @@ pgstat_drop_relation(Relation rel)
 
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
 							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  RelationGetRelid(rel), InvalidOid);
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -225,7 +227,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											dboid, tableoid, InvalidOid, false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -318,6 +320,7 @@ pgstat_report_analyze(Relation rel,
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
 											RelationGetRelid(rel),
+											InvalidOid,
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -458,6 +461,19 @@ pgstat_fetch_stat_tabentry(Oid relid)
 	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
 }
 
+/*
+ * Support function for the SQL-callable pgstat* functions. Returns
+ * the collected statistics for one relfilenode or NULL. NULL doesn't mean
+ * that the relfilenode doesn't exist, just that there are no statistics, so the
+ * caller is better off to report ZERO instead.
+ */
+PgStat_StatRelFileNodeEntry *
+pgstat_fetch_stat_relfilenodeentry(Oid dboid, Oid spcOid, RelFileNumber relfile)
+{
+	return (PgStat_StatRelFileNodeEntry *)
+		pgstat_fetch_entry(PGSTAT_KIND_RELFILENODE, dboid, spcOid, relfile);
+}
+
 /*
  * More efficient version of pgstat_fetch_stat_tabentry(), allowing to specify
  * whether the to-be-accessed table is a shared relation or not.
@@ -468,7 +484,7 @@ pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
 	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 
 	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid, InvalidOid);
 }
 
 /*
@@ -491,10 +507,10 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id, InvalidOid);
 	if (!entry_ref)
 	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
+		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id, InvalidOid);
 		if (!entry_ref)
 			return tablestatus;
 	}
@@ -881,6 +897,38 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 	return true;
 }
 
+/*
+ * Flush out pending stats for the relfilenode entry
+ *
+ * If nowait is true, this function returns false if lock could not
+ * immediately acquired, otherwise true is returned.
+ */
+bool
+pgstat_relfilenode_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_RelFileNode *sharedent;
+	PgStat_StatRelFileNodeEntry *pendingent;
+
+	pendingent = (PgStat_StatRelFileNodeEntry *) entry_ref->pending;
+	sharedent = (PgStatShared_RelFileNode *) entry_ref->shared_stats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+#define PGSTAT_ACCUM_RELFILENODECOUNT(item)      \
+		(sharedent)->stats.item += (pendingent)->item
+
+	PGSTAT_ACCUM_RELFILENODECOUNT(blocks_fetched);
+	PGSTAT_ACCUM_RELFILENODECOUNT(blocks_hit);
+	PGSTAT_ACCUM_RELFILENODECOUNT(blocks_written);
+
+	pgstat_unlock_entry(entry_ref);
+
+	memset(pendingent, 0, sizeof(*pendingent));
+
+	return true;
+}
+
 void
 pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref)
 {
@@ -902,7 +950,7 @@ pgstat_prep_relation_pending(Oid rel_id, bool isshared)
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
 										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  rel_id, InvalidOid, NULL);
 	pending = entry_ref->pending;
 	pending->id = rel_id;
 	pending->shared = isshared;
@@ -910,6 +958,56 @@ pgstat_prep_relation_pending(Oid rel_id, bool isshared)
 	return pending;
 }
 
+PgStat_StatRelFileNodeEntry *
+pgstat_prep_relfilenode_pending(RelFileLocator locator)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELFILENODE, locator.dbOid,
+										  locator.spcOid, locator.relNumber, NULL);
+
+	return entry_ref->pending;
+}
+
+void
+pgstat_report_relfilenode_blks_written(RelFileLocator locator)
+{
+	PgStat_StatRelFileNodeEntry *relfileentry = NULL;
+
+	relfileentry = pgstat_prep_relfilenode_pending(locator);
+
+	if (relfileentry)
+		relfileentry->blocks_written++;
+}
+
+void
+pgstat_report_relfilenode_buffer_read(Relation reln)
+{
+	PgStat_StatRelFileNodeEntry *relfileentry = NULL;
+
+	/* For relation stats to survive after a rewrite */
+	pgstat_count_buffer_read(reln);
+
+	relfileentry = pgstat_prep_relfilenode_pending(reln->rd_locator);
+
+	if (relfileentry)
+		relfileentry->blocks_fetched++;
+}
+
+void
+pgstat_report_relfilenode_buffer_hit(Relation reln)
+{
+	PgStat_StatRelFileNodeEntry *relfileentry = NULL;
+
+	/* For relation stats to survive after a rewrite */
+	pgstat_count_buffer_hit(reln);
+
+	relfileentry = pgstat_prep_relfilenode_pending(reln->rd_locator);
+
+	if (relfileentry)
+		relfileentry->blocks_hit++;
+}
+
 /*
  * add a new (sub)transaction state record
  */
diff --git a/src/backend/utils/activity/pgstat_replslot.c b/src/backend/utils/activity/pgstat_replslot.c
index da11b86744..2e68ed4a09 100644
--- a/src/backend/utils/activity/pgstat_replslot.c
+++ b/src/backend/utils/activity/pgstat_replslot.c
@@ -62,7 +62,7 @@ pgstat_reset_replslot(const char *name)
 	 */
 	if (SlotIsLogical(slot))
 		pgstat_reset(PGSTAT_KIND_REPLSLOT, InvalidOid,
-					 ReplicationSlotIndex(slot));
+					 ReplicationSlotIndex(slot), InvalidOid);
 
 	LWLockRelease(ReplicationSlotControlLock);
 }
@@ -82,7 +82,7 @@ pgstat_report_replslot(ReplicationSlot *slot, const PgStat_StatReplSlotEntry *re
 	PgStat_StatReplSlotEntry *statent;
 
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_REPLSLOT, InvalidOid,
-											ReplicationSlotIndex(slot), false);
+											ReplicationSlotIndex(slot), InvalidOid, false);
 	shstatent = (PgStatShared_ReplSlot *) entry_ref->shared_stats;
 	statent = &shstatent->stats;
 
@@ -116,7 +116,7 @@ pgstat_create_replslot(ReplicationSlot *slot)
 	Assert(LWLockHeldByMeInMode(ReplicationSlotAllocationLock, LW_EXCLUSIVE));
 
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_REPLSLOT, InvalidOid,
-											ReplicationSlotIndex(slot), false);
+											ReplicationSlotIndex(slot), InvalidOid, false);
 	shstatent = (PgStatShared_ReplSlot *) entry_ref->shared_stats;
 
 	/*
@@ -146,7 +146,7 @@ void
 pgstat_acquire_replslot(ReplicationSlot *slot)
 {
 	pgstat_get_entry_ref(PGSTAT_KIND_REPLSLOT, InvalidOid,
-						 ReplicationSlotIndex(slot), true, NULL);
+						 ReplicationSlotIndex(slot), InvalidOid, true, NULL);
 }
 
 /*
@@ -158,7 +158,7 @@ pgstat_drop_replslot(ReplicationSlot *slot)
 	Assert(LWLockHeldByMeInMode(ReplicationSlotAllocationLock, LW_EXCLUSIVE));
 
 	if (!pgstat_drop_entry(PGSTAT_KIND_REPLSLOT, InvalidOid,
-						   ReplicationSlotIndex(slot)))
+						   ReplicationSlotIndex(slot), InvalidOid))
 		pgstat_request_entry_refs_gc();
 }
 
@@ -178,7 +178,7 @@ pgstat_fetch_replslot(NameData slotname)
 
 	if (idx != -1)
 		slotentry = (PgStat_StatReplSlotEntry *) pgstat_fetch_entry(PGSTAT_KIND_REPLSLOT,
-																	InvalidOid, idx);
+																	InvalidOid, idx, InvalidOid);
 
 	LWLockRelease(ReplicationSlotControlLock);
 
@@ -210,6 +210,7 @@ pgstat_replslot_from_serialized_name_cb(const NameData *name, PgStat_HashKey *ke
 	key->kind = PGSTAT_KIND_REPLSLOT;
 	key->dboid = InvalidOid;
 	key->objoid = idx;
+	key->relfile = InvalidOid;
 
 	return true;
 }
diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c
index 4a4b69891d..047e81f756 100644
--- a/src/backend/utils/activity/pgstat_shmem.c
+++ b/src/backend/utils/activity/pgstat_shmem.c
@@ -395,10 +395,10 @@ pgstat_get_entry_ref_cached(PgStat_HashKey key, PgStat_EntryRef **entry_ref_p)
  * if the entry is newly created, false otherwise.
  */
 PgStat_EntryRef *
-pgstat_get_entry_ref(PgStat_Kind kind, Oid dboid, Oid objoid, bool create,
-					 bool *created_entry)
+pgstat_get_entry_ref(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile,
+					 bool create, bool *created_entry)
 {
-	PgStat_HashKey key = {.kind = kind,.dboid = dboid,.objoid = objoid};
+	PgStat_HashKey key = {.kind = kind,.dboid = dboid,.objoid = objoid,.relfile = relfile};
 	PgStatShared_HashEntry *shhashent;
 	PgStatShared_Common *shheader = NULL;
 	PgStat_EntryRef *entry_ref;
@@ -611,12 +611,12 @@ pgstat_unlock_entry(PgStat_EntryRef *entry_ref)
  */
 PgStat_EntryRef *
 pgstat_get_entry_ref_locked(PgStat_Kind kind, Oid dboid, Oid objoid,
-							bool nowait)
+							RelFileNumber relfile, bool nowait)
 {
 	PgStat_EntryRef *entry_ref;
 
 	/* find shared table stats entry corresponding to the local entry */
-	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, true, NULL);
+	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, relfile, true, NULL);
 
 	/* lock the shared entry to protect the content, skip if failed */
 	if (!pgstat_lock_entry(entry_ref, nowait))
@@ -867,9 +867,9 @@ pgstat_drop_database_and_contents(Oid dboid)
  * pgstat_gc_entry_refs().
  */
 bool
-pgstat_drop_entry(PgStat_Kind kind, Oid dboid, Oid objoid)
+pgstat_drop_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile)
 {
-	PgStat_HashKey key = {.kind = kind,.dboid = dboid,.objoid = objoid};
+	PgStat_HashKey key = {.kind = kind,.dboid = dboid,.objoid = objoid,.relfile = relfile};
 	PgStatShared_HashEntry *shent;
 	bool		freed = true;
 
@@ -942,13 +942,12 @@ shared_stat_reset_contents(PgStat_Kind kind, PgStatShared_Common *header,
  * Reset one variable-numbered stats entry.
  */
 void
-pgstat_reset_entry(PgStat_Kind kind, Oid dboid, Oid objoid, TimestampTz ts)
+pgstat_reset_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile, TimestampTz ts)
 {
 	PgStat_EntryRef *entry_ref;
 
 	Assert(!pgstat_get_kind_info(kind)->fixed_amount);
-
-	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, false, NULL);
+	entry_ref = pgstat_get_entry_ref(kind, dboid, objoid, relfile, false, NULL);
 	if (!entry_ref || entry_ref->shared_entry->dropped)
 		return;
 
diff --git a/src/backend/utils/activity/pgstat_subscription.c b/src/backend/utils/activity/pgstat_subscription.c
index d9af8de658..9b9ab2861b 100644
--- a/src/backend/utils/activity/pgstat_subscription.c
+++ b/src/backend/utils/activity/pgstat_subscription.c
@@ -30,7 +30,7 @@ pgstat_report_subscription_error(Oid subid, bool is_apply_error)
 	PgStat_BackendSubEntry *pending;
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_SUBSCRIPTION,
-										  InvalidOid, subid, NULL);
+										  InvalidOid, subid, InvalidOid, NULL);
 	pending = entry_ref->pending;
 
 	if (is_apply_error)
@@ -47,12 +47,12 @@ pgstat_create_subscription(Oid subid)
 {
 	/* Ensures that stats are dropped if transaction rolls back */
 	pgstat_create_transactional(PGSTAT_KIND_SUBSCRIPTION,
-								InvalidOid, subid);
+								InvalidOid, subid, InvalidOid);
 
 	/* Create and initialize the subscription stats entry */
-	pgstat_get_entry_ref(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid,
+	pgstat_get_entry_ref(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid, InvalidOid,
 						 true, NULL);
-	pgstat_reset_entry(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid, 0);
+	pgstat_reset_entry(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid, InvalidOid, 0);
 }
 
 /*
@@ -64,7 +64,7 @@ void
 pgstat_drop_subscription(Oid subid)
 {
 	pgstat_drop_transactional(PGSTAT_KIND_SUBSCRIPTION,
-							  InvalidOid, subid);
+							  InvalidOid, subid, InvalidOid);
 }
 
 /*
@@ -75,7 +75,7 @@ PgStat_StatSubEntry *
 pgstat_fetch_stat_subscription(Oid subid)
 {
 	return (PgStat_StatSubEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid);
+		pgstat_fetch_entry(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid, InvalidOid);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_xact.c b/src/backend/utils/activity/pgstat_xact.c
index 1877d22f14..b25df5112b 100644
--- a/src/backend/utils/activity/pgstat_xact.c
+++ b/src/backend/utils/activity/pgstat_xact.c
@@ -30,7 +30,7 @@ static void AtEOXact_PgStat_DroppedStats(PgStat_SubXactStatus *xact_state, bool
 static void AtEOSubXact_PgStat_DroppedStats(PgStat_SubXactStatus *xact_state,
 											bool isCommit, int nestDepth);
 
-static PgStat_SubXactStatus *pgStatXactStack = NULL;
+PgStat_SubXactStatus *pgStatXactStack = NULL;
 
 
 /*
@@ -84,7 +84,7 @@ AtEOXact_PgStat_DroppedStats(PgStat_SubXactStatus *xact_state, bool isCommit)
 			 * Transaction that dropped an object committed. Drop the stats
 			 * too.
 			 */
-			if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid))
+			if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid, it->relfile))
 				not_freed_count++;
 		}
 		else if (!isCommit && pending->is_create)
@@ -93,7 +93,7 @@ AtEOXact_PgStat_DroppedStats(PgStat_SubXactStatus *xact_state, bool isCommit)
 			 * Transaction that created an object aborted. Drop the stats
 			 * associated with the object.
 			 */
-			if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid))
+			if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid, it->relfile))
 				not_freed_count++;
 		}
 
@@ -105,6 +105,33 @@ AtEOXact_PgStat_DroppedStats(PgStat_SubXactStatus *xact_state, bool isCommit)
 		pgstat_request_entry_refs_gc();
 }
 
+/*
+ * Remove a relfilenode stat from the list of stats to be dropped.
+ */
+void
+PgStat_RemoveRelFileNodeFromDroppedStats(PgStat_SubXactStatus *xact_state, RelFileLocator rlocator)
+{
+	dlist_mutable_iter iter;
+
+	if (dclist_count(&xact_state->pending_drops) == 0)
+		return;
+
+	dclist_foreach_modify(iter, &xact_state->pending_drops)
+	{
+		PgStat_PendingDroppedStatsItem *pending =
+			dclist_container(PgStat_PendingDroppedStatsItem, node, iter.cur);
+		xl_xact_stats_item *it = &pending->item;
+
+		if (it->kind == PGSTAT_KIND_RELFILENODE && it->dboid == rlocator.dbOid
+			&& it->objoid == rlocator.spcOid && it->relfile == rlocator.relNumber)
+		{
+			dclist_delete_from(&xact_state->pending_drops, &pending->node);
+			pfree(pending);
+			return;
+		}
+	}
+}
+
 /*
  * Called from access/transam/xact.c at subtransaction commit/abort.
  */
@@ -158,7 +185,7 @@ AtEOSubXact_PgStat_DroppedStats(PgStat_SubXactStatus *xact_state,
 			 * Subtransaction creating a new stats object aborted. Drop the
 			 * stats object.
 			 */
-			if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid))
+			if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid, it->relfile))
 				not_freed_count++;
 			pfree(pending);
 		}
@@ -320,7 +347,11 @@ pgstat_execute_transactional_drops(int ndrops, struct xl_xact_stats_item *items,
 	{
 		xl_xact_stats_item *it = &items[i];
 
-		if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid))
+		/* leave it to pgstat_drop_transactional() in RelationDropStorage() */
+		if (it->kind == PGSTAT_KIND_RELFILENODE)
+			continue;
+
+		if (!pgstat_drop_entry(it->kind, it->dboid, it->objoid, it->relfile))
 			not_freed_count++;
 	}
 
@@ -329,7 +360,7 @@ pgstat_execute_transactional_drops(int ndrops, struct xl_xact_stats_item *items,
 }
 
 static void
-create_drop_transactional_internal(PgStat_Kind kind, Oid dboid, Oid objoid, bool is_create)
+create_drop_transactional_internal(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile, bool is_create)
 {
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_SubXactStatus *xact_state;
@@ -342,6 +373,7 @@ create_drop_transactional_internal(PgStat_Kind kind, Oid dboid, Oid objoid, bool
 	drop->item.kind = kind;
 	drop->item.dboid = dboid;
 	drop->item.objoid = objoid;
+	drop->item.relfile = relfile;
 
 	dclist_push_tail(&xact_state->pending_drops, &drop->node);
 }
@@ -354,18 +386,18 @@ create_drop_transactional_internal(PgStat_Kind kind, Oid dboid, Oid objoid, bool
  * dropped.
  */
 void
-pgstat_create_transactional(PgStat_Kind kind, Oid dboid, Oid objoid)
+pgstat_create_transactional(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile)
 {
-	if (pgstat_get_entry_ref(kind, dboid, objoid, false, NULL))
+	if (pgstat_get_entry_ref(kind, dboid, objoid, relfile, false, NULL))
 	{
 		ereport(WARNING,
-				errmsg("resetting existing statistics for kind %s, db=%u, oid=%u",
-					   (pgstat_get_kind_info(kind))->name, dboid, objoid));
+				errmsg("resetting existing statistics for kind %s, db=%u, oid=%u, relfile=%u",
+					   (pgstat_get_kind_info(kind))->name, dboid, objoid, relfile));
 
-		pgstat_reset(kind, dboid, objoid);
+		pgstat_reset(kind, dboid, objoid, relfile);
 	}
 
-	create_drop_transactional_internal(kind, dboid, objoid, /* create */ true);
+	create_drop_transactional_internal(kind, dboid, objoid, relfile, /* create */ true);
 }
 
 /*
@@ -376,7 +408,7 @@ pgstat_create_transactional(PgStat_Kind kind, Oid dboid, Oid objoid)
  * alive.
  */
 void
-pgstat_drop_transactional(PgStat_Kind kind, Oid dboid, Oid objoid)
+pgstat_drop_transactional(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile)
 {
-	create_drop_transactional_internal(kind, dboid, objoid, /* create */ false);
+	create_drop_transactional_internal(kind, dboid, objoid, relfile, /* create */ false);
 }
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 3876339ee1..e266d96f5e 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -106,6 +106,30 @@ PG_STAT_GET_RELENTRY_INT64(tuples_updated)
 /* pg_stat_get_vacuum_count */
 PG_STAT_GET_RELENTRY_INT64(vacuum_count)
 
+#define PG_STAT_GET_RELFILEENTRY_INT64(stat)						\
+Datum															\
+CppConcat(pg_stat_get_relfilenode_,stat)(PG_FUNCTION_ARGS)					\
+{																\
+	Oid			dboid = PG_GETARG_OID(0);						\
+	Oid			 spcOid = PG_GETARG_OID(1);						\
+	RelFileNumber			 relfile = PG_GETARG_OID(2);						\
+	int64		result;											\
+	PgStat_StatRelFileNodeEntry *relfileentry;								\
+																\
+	if ((relfileentry = pgstat_fetch_stat_relfilenodeentry(dboid, spcOid, relfile)) == NULL)	\
+		result = 0;												\
+	else														\
+		result = (int64) (relfileentry->stat);						\
+																\
+	PG_RETURN_INT64(result);									\
+}
+
+/* pg_stat_get_relfilenode_blocks_written */
+PG_STAT_GET_RELFILEENTRY_INT64(blocks_written)
+
+/* pg_stat_get_blocks_written */
+PG_STAT_GET_RELENTRY_INT64(blocks_written)
+
 #define PG_STAT_GET_RELENTRY_TIMESTAMPTZ(stat)					\
 Datum															\
 CppConcat(pg_stat_get_,stat)(PG_FUNCTION_ARGS)					\
@@ -1752,7 +1776,7 @@ pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 	Oid			taboid = PG_GETARG_OID(0);
 	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid, InvalidOid);
 
 	PG_RETURN_VOID();
 }
@@ -1762,7 +1786,7 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 {
 	Oid			funcoid = PG_GETARG_OID(0);
 
-	pgstat_reset(PGSTAT_KIND_FUNCTION, MyDatabaseId, funcoid);
+	pgstat_reset(PGSTAT_KIND_FUNCTION, MyDatabaseId, funcoid, InvalidOid);
 
 	PG_RETURN_VOID();
 }
@@ -1820,7 +1844,7 @@ pg_stat_reset_subscription_stats(PG_FUNCTION_ARGS)
 			ereport(ERROR,
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 					 errmsg("invalid subscription OID %u", subid)));
-		pgstat_reset(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid);
+		pgstat_reset(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid, InvalidOid);
 	}
 
 	PG_RETURN_VOID();
@@ -2028,7 +2052,9 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	char	   *stats_type = text_to_cstring(PG_GETARG_TEXT_P(0));
 	Oid			dboid = PG_GETARG_OID(1);
 	Oid			objoid = PG_GETARG_OID(2);
+	Oid			relfile = PG_GETARG_OID(3);
+
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
-	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objoid));
+	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objoid, relfile));
 }
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index 8e583b45cd..792cd2237e 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -21,7 +21,9 @@
 #include "access/sdir.h"
 #include "access/xact.h"
 #include "executor/tuptable.h"
+#include "pgstat.h"
 #include "storage/read_stream.h"
+#include "utils/pgstat_internal.h"
 #include "utils/rel.h"
 #include "utils/snapshot.h"
 
@@ -1634,6 +1636,23 @@ table_relation_set_new_filelocator(Relation rel,
 								   TransactionId *freezeXid,
 								   MultiXactId *minmulti)
 {
+	PgStat_StatRelFileNodeEntry *relfileentry;
+	PgStat_StatTabEntry *tabentry = NULL;
+	PgStat_EntryRef *entry_ref = NULL;
+	PgStatShared_Relation *shtabentry;
+
+	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_RELATION, MyDatabaseId, rel->rd_id, InvalidOid, false, NULL);
+	if (entry_ref)
+	{
+		shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
+		tabentry = &shtabentry->stats;
+	}
+
+	relfileentry = pgstat_fetch_stat_relfilenodeentry(rel->rd_locator.dbOid, rel->rd_locator.spcOid, rel->rd_locator.relNumber);
+
+	if (tabentry && relfileentry)
+		tabentry->blocks_written += relfileentry->blocks_written;
+
 	rel->rd_tableam->relation_set_new_filelocator(rel, newrlocator,
 												  persistence, freezeXid,
 												  minmulti);
diff --git a/src/include/access/xact.h b/src/include/access/xact.h
index 6d4439f052..3b9ed65ff6 100644
--- a/src/include/access/xact.h
+++ b/src/include/access/xact.h
@@ -284,6 +284,7 @@ typedef struct xl_xact_stats_item
 	int			kind;
 	Oid			dboid;
 	Oid			objoid;
+	RelFileNumber relfile;
 } xl_xact_stats_item;
 
 typedef struct xl_xact_stats_items
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6a5476d3c4..912471a1ac 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5374,6 +5374,14 @@
   proname => 'pg_stat_get_tuples_updated', provolatile => 's',
   proparallel => 'r', prorettype => 'int8', proargtypes => 'oid',
   prosrc => 'pg_stat_get_tuples_updated' },
+{ oid => '9280', descr => 'statistics: number of blocks written',
+  proname => 'pg_stat_get_relfilenode_blocks_written', provolatile => 's',
+  proparallel => 'r',
+  proargtypes => 'oid oid oid',
+  prorettype => 'int8',
+  proallargtypes => '{oid,oid,oid,int8}',
+  proargmodes => '{i,i,i,o}',
+  prosrc => 'pg_stat_get_relfilenode_blocks_written' },
 { oid => '1933', descr => 'statistics: number of tuples deleted',
   proname => 'pg_stat_get_tuples_deleted', provolatile => 's',
   proparallel => 'r', prorettype => 'int8', proargtypes => 'oid',
@@ -5413,6 +5421,10 @@
   proname => 'pg_stat_get_blocks_hit', provolatile => 's', proparallel => 'r',
   prorettype => 'int8', proargtypes => 'oid',
   prosrc => 'pg_stat_get_blocks_hit' },
+{ oid => '8438', descr => 'statistics: number of blocks written',
+  proname => 'pg_stat_get_blocks_written', provolatile => 's', proparallel => 'r',
+  prorettype => 'int8', proargtypes => 'oid',
+  prosrc => 'pg_stat_get_blocks_written' },
 { oid => '2781', descr => 'statistics: last manual vacuum time for a table',
   proname => 'pg_stat_get_last_vacuum_time', provolatile => 's',
   proparallel => 'r', prorettype => 'timestamptz', proargtypes => 'oid',
@@ -5499,7 +5511,7 @@
 
 { oid => '6230', descr => 'statistics: check if a stats object exists',
   proname => 'pg_stat_have_stats', provolatile => 'v', proparallel => 'r',
-  prorettype => 'bool', proargtypes => 'text oid oid',
+  prorettype => 'bool', proargtypes => 'text oid oid oid',
   prosrc => 'pg_stat_have_stats' },
 
 { oid => '6231', descr => 'statistics: information about subscription stats',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 2136239710..9631689430 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -14,6 +14,7 @@
 #include "datatype/timestamp.h"
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */
 #include "utils/backend_status.h"	/* for backward compatibility */
 #include "utils/relcache.h"
@@ -40,6 +41,7 @@ typedef enum PgStat_Kind
 	/* stats for variable-numbered objects */
 	PGSTAT_KIND_DATABASE,		/* database-wide statistics */
 	PGSTAT_KIND_RELATION,		/* per-table statistics */
+	PGSTAT_KIND_RELFILENODE,	/* per-relfilenode statistics */
 	PGSTAT_KIND_FUNCTION,		/* per-function statistics */
 	PGSTAT_KIND_REPLSLOT,		/* per-slot statistics */
 	PGSTAT_KIND_SUBSCRIPTION,	/* per-subscription statistics */
@@ -417,6 +419,7 @@ typedef struct PgStat_StatTabEntry
 
 	PgStat_Counter blocks_fetched;
 	PgStat_Counter blocks_hit;
+	PgStat_Counter blocks_written;
 
 	TimestampTz last_vacuum_time;	/* user initiated vacuum */
 	PgStat_Counter vacuum_count;
@@ -428,6 +431,13 @@ typedef struct PgStat_StatTabEntry
 	PgStat_Counter autoanalyze_count;
 } PgStat_StatTabEntry;
 
+typedef struct PgStat_StatRelFileNodeEntry
+{
+	PgStat_Counter blocks_fetched;
+	PgStat_Counter blocks_hit;
+	PgStat_Counter blocks_written;
+} PgStat_StatRelFileNodeEntry;
+
 typedef struct PgStat_WalStats
 {
 	PgStat_Counter wal_records;
@@ -478,7 +488,7 @@ extern long pgstat_report_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
 extern void pgstat_reset_counters(void);
-extern void pgstat_reset(PgStat_Kind kind, Oid dboid, Oid objoid);
+extern void pgstat_reset(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile);
 extern void pgstat_reset_of_kind(PgStat_Kind kind);
 
 /* stats accessors */
@@ -487,7 +497,7 @@ extern TimestampTz pgstat_get_stat_snapshot_timestamp(bool *have_snapshot);
 
 /* helpers */
 extern PgStat_Kind pgstat_get_kind_from_str(char *kind_str);
-extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, Oid objoid);
+extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile);
 
 
 /*
@@ -596,6 +606,10 @@ extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
 								  bool resetcounter);
 
+extern void pgstat_report_relfilenode_blks_written(RelFileLocator locator);
+extern void pgstat_report_relfilenode_buffer_read(Relation reln);
+extern void pgstat_report_relfilenode_buffer_hit(Relation reln);
+
 /*
  * If stats are enabled, but pending data hasn't been prepared yet, call
  * pgstat_assoc_relation() to do so. See its comment for why this is done
@@ -655,6 +669,7 @@ extern void pgstat_twophase_postabort(TransactionId xid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
+extern PgStat_StatRelFileNodeEntry *pgstat_fetch_stat_relfilenodeentry(Oid dboid, Oid spcOid, RelFileNumber relfile);
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
 														   Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index dbbca31602..50d5f1a577 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -53,7 +53,8 @@ typedef struct PgStat_HashKey
 {
 	PgStat_Kind kind;			/* statistics entry kind */
 	Oid			dboid;			/* database ID. InvalidOid for shared objects. */
-	Oid			objoid;			/* object ID, either table or function. */
+	Oid			objoid;			/* object ID, either table or function or tablespace. */
+	RelFileNumber relfile;		/* relfilenumber for RelFileLocator. */
 } PgStat_HashKey;
 
 /*
@@ -376,6 +377,12 @@ typedef struct PgStatShared_Relation
 	PgStat_StatTabEntry stats;
 } PgStatShared_Relation;
 
+typedef struct PgStatShared_RelFileNode
+{
+	PgStatShared_Common header;
+	PgStat_StatRelFileNodeEntry stats;
+} PgStatShared_RelFileNode;
+
 typedef struct PgStatShared_Function
 {
 	PgStatShared_Common header;
@@ -498,6 +505,9 @@ static inline size_t pgstat_get_entry_len(PgStat_Kind kind);
 static inline void *pgstat_get_entry_data(PgStat_Kind kind, PgStatShared_Common *entry);
 
 
+extern PgStat_SubXactStatus *pgStatXactStack;
+extern void PgStat_RemoveRelFileNodeFromDroppedStats(PgStat_SubXactStatus *xact_state, RelFileLocator rlocator);
+
 /*
  * Functions in pgstat.c
  */
@@ -511,10 +521,12 @@ extern void pgstat_assert_is_up(void);
 #endif
 
 extern void pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref);
-extern PgStat_EntryRef *pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid, bool *created_entry);
-extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid);
+extern PgStat_EntryRef *pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid,
+												  Oid objoid, RelFileNumber relfile,
+												  bool *created_entry);
+extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile);
 
-extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, Oid objoid);
+extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
 
 
@@ -582,6 +594,7 @@ extern void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_relfilenode_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 
 
@@ -602,15 +615,16 @@ extern void pgstat_attach_shmem(void);
 extern void pgstat_detach_shmem(void);
 
 extern PgStat_EntryRef *pgstat_get_entry_ref(PgStat_Kind kind, Oid dboid, Oid objoid,
-											 bool create, bool *created_entry);
+											 RelFileNumber relfile, bool create,
+											 bool *created_entry);
 extern bool pgstat_lock_entry(PgStat_EntryRef *entry_ref, bool nowait);
 extern bool pgstat_lock_entry_shared(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_unlock_entry(PgStat_EntryRef *entry_ref);
-extern bool pgstat_drop_entry(PgStat_Kind kind, Oid dboid, Oid objoid);
+extern bool pgstat_drop_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile);
 extern void pgstat_drop_all_entries(void);
 extern PgStat_EntryRef *pgstat_get_entry_ref_locked(PgStat_Kind kind, Oid dboid, Oid objoid,
-													bool nowait);
-extern void pgstat_reset_entry(PgStat_Kind kind, Oid dboid, Oid objoid, TimestampTz ts);
+													RelFileNumber relfile, bool nowait);
+extern void pgstat_reset_entry(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile, TimestampTz ts);
 extern void pgstat_reset_entries_of_kind(PgStat_Kind kind, TimestampTz ts);
 extern void pgstat_reset_matching_entries(bool (*do_reset) (PgStatShared_HashEntry *, Datum),
 										  Datum match_data,
@@ -655,8 +669,8 @@ extern void pgstat_subscription_reset_timestamp_cb(PgStatShared_Common *header,
  */
 
 extern PgStat_SubXactStatus *pgstat_get_xact_stack_level(int nest_level);
-extern void pgstat_drop_transactional(PgStat_Kind kind, Oid dboid, Oid objoid);
-extern void pgstat_create_transactional(PgStat_Kind kind, Oid dboid, Oid objoid);
+extern void pgstat_drop_transactional(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile);
+extern void pgstat_create_transactional(PgStat_Kind kind, Oid dboid, Oid objoid, RelFileNumber relfile);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 6a1615a1e8..ee5a404b45 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -40,10 +40,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 my $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats('database', $dboid, 0, 0), 't', "$sect: db stats do exist");
+is(have_stats('function', $dboid, $funcoid, 0),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats('relation', $dboid, $tableoid, 0),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -64,10 +64,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats('database', $dboid, 0, 0), 't', "$sect: db stats do exist");
+is(have_stats('function', $dboid, $funcoid, 0),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats('relation', $dboid, $tableoid, 0),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -81,10 +81,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats('database', $dboid, 0, 0), 'f', "$sect: db stats do not exist");
+is(have_stats('function', $dboid, $funcoid, 0),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats('relation', $dboid, $tableoid, 0),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -95,10 +95,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats('database', $dboid, 0, 0), 't', "$sect: db stats do exist");
+is(have_stats('function', $dboid, $funcoid, 0),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats('relation', $dboid, $tableoid, 0),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -114,10 +114,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats('database', $dboid, 0, 0), 'f', "$sect: db stats do not exist");
+is(have_stats('function', $dboid, $funcoid, 0),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats('relation', $dboid, $tableoid, 0),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -130,10 +130,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats('database', $dboid, 0, 0), 'f', "$sect: db stats do not exist");
+is(have_stats('function', $dboid, $funcoid, 0),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats('relation', $dboid, $tableoid, 0),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -292,10 +292,10 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objoid) = @_;
+	my ($kind, $dboid, $objoid, $relfile) = @_;
 
 	return $node->safe_psql($connect_db,
-		"SELECT pg_stat_have_stats('$kind', $dboid, $objoid)");
+		"SELECT pg_stat_have_stats('$kind', $dboid, $objoid, $relfile)");
 }
 
 sub overwrite_file
diff --git a/src/test/recovery/t/030_stats_cleanup_replica.pl b/src/test/recovery/t/030_stats_cleanup_replica.pl
index 74b516cc7c..317df24c4f 100644
--- a/src/test/recovery/t/030_stats_cleanup_replica.pl
+++ b/src/test/recovery/t/030_stats_cleanup_replica.pl
@@ -179,9 +179,9 @@ sub test_standby_func_tab_stats_status
 	my %stats;
 
 	$stats{rel} = $node_standby->safe_psql($connect_db,
-		"SELECT pg_stat_have_stats('relation', $dboid, $tableoid)");
+		"SELECT pg_stat_have_stats('relation', $dboid, $tableoid, 0)");
 	$stats{func} = $node_standby->safe_psql($connect_db,
-		"SELECT pg_stat_have_stats('function', $dboid, $funcoid)");
+		"SELECT pg_stat_have_stats('function', $dboid, $funcoid, 0)");
 
 	is_deeply(\%stats, \%expected, "$sect: standby stats as expected");
 
@@ -194,7 +194,7 @@ sub test_standby_db_stats_status
 	my ($connect_db, $dboid, $present) = @_;
 
 	is( $node_standby->safe_psql(
-			$connect_db, "SELECT pg_stat_have_stats('database', $dboid, 0)"),
+			$connect_db, "SELECT pg_stat_have_stats('database', $dboid, 0, 0)"),
 		$present,
 		"$sect: standby db stats as expected");
 }
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index ef658ad740..a2fa165c4c 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -2335,6 +2335,11 @@ pg_statio_all_tables| SELECT c.oid AS relid,
     n.nspname AS schemaname,
     c.relname,
     (pg_stat_get_blocks_fetched(c.oid) - pg_stat_get_blocks_hit(c.oid)) AS heap_blks_read,
+    (pg_stat_get_blocks_written(c.oid) + pg_stat_get_relfilenode_blocks_written(d.oid,
+        CASE
+            WHEN (c.reltablespace <> (0)::oid) THEN c.reltablespace
+            ELSE d.dattablespace
+        END, c.relfilenode)) AS heap_blks_written,
     pg_stat_get_blocks_hit(c.oid) AS heap_blks_hit,
     i.idx_blks_read,
     i.idx_blks_hit,
@@ -2342,7 +2347,8 @@ pg_statio_all_tables| SELECT c.oid AS relid,
     pg_stat_get_blocks_hit(t.oid) AS toast_blks_hit,
     x.idx_blks_read AS tidx_blks_read,
     x.idx_blks_hit AS tidx_blks_hit
-   FROM ((((pg_class c
+   FROM pg_database d,
+    ((((pg_class c
      LEFT JOIN pg_class t ON ((c.reltoastrelid = t.oid)))
      LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
      LEFT JOIN LATERAL ( SELECT (sum((pg_stat_get_blocks_fetched(pg_index.indexrelid) - pg_stat_get_blocks_hit(pg_index.indexrelid))))::bigint AS idx_blks_read,
@@ -2353,7 +2359,7 @@ pg_statio_all_tables| SELECT c.oid AS relid,
             (sum(pg_stat_get_blocks_hit(pg_index.indexrelid)))::bigint AS idx_blks_hit
            FROM pg_index
           WHERE (pg_index.indrelid = t.oid)) x ON (true))
-  WHERE (c.relkind = ANY (ARRAY['r'::"char", 't'::"char", 'm'::"char"]));
+  WHERE ((c.relkind = ANY (ARRAY['r'::"char", 't'::"char", 'm'::"char"])) AND (d.datname = current_database()));
 pg_statio_sys_indexes| SELECT relid,
     indexrelid,
     schemaname,
@@ -2374,6 +2380,7 @@ pg_statio_sys_tables| SELECT relid,
     schemaname,
     relname,
     heap_blks_read,
+    heap_blks_written,
     heap_blks_hit,
     idx_blks_read,
     idx_blks_hit,
@@ -2403,6 +2410,7 @@ pg_statio_user_tables| SELECT relid,
     schemaname,
     relname,
     heap_blks_read,
+    heap_blks_written,
     heap_blks_hit,
     idx_blks_read,
     idx_blks_hit,
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 6e08898b18..eff0c9372c 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1111,23 +1111,23 @@ ROLLBACK;
 -- pg_stat_have_stats behavior
 ----
 -- fixed-numbered stats exist
-SELECT pg_stat_have_stats('bgwriter', 0, 0);
+SELECT pg_stat_have_stats('bgwriter', 0, 0, 0);
  pg_stat_have_stats 
 --------------------
  t
 (1 row)
 
 -- unknown stats kinds error out
-SELECT pg_stat_have_stats('zaphod', 0, 0);
+SELECT pg_stat_have_stats('zaphod', 0, 0, 0);
 ERROR:  invalid statistics kind: "zaphod"
 -- db stats have objoid 0
-SELECT pg_stat_have_stats('database', :dboid, 1);
+SELECT pg_stat_have_stats('database', :dboid, 1, 0);
  pg_stat_have_stats 
 --------------------
  f
 (1 row)
 
-SELECT pg_stat_have_stats('database', :dboid, 0);
+SELECT pg_stat_have_stats('database', :dboid, 0, 0);
  pg_stat_have_stats 
 --------------------
  t
@@ -1144,21 +1144,21 @@ select a from stats_test_tab1 where a = 3;
  3
 (1 row)
 
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  t
 (1 row)
 
 -- pg_stat_have_stats returns false for dropped index with stats
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  t
 (1 row)
 
 DROP index stats_test_idx1;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  f
@@ -1174,14 +1174,14 @@ select a from stats_test_tab1 where a = 3;
  3
 (1 row)
 
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  t
 (1 row)
 
 ROLLBACK;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  f
@@ -1196,7 +1196,7 @@ select a from stats_test_tab1 where a = 3;
  3
 (1 row)
 
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  t
@@ -1204,7 +1204,7 @@ SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
 
 REINDEX index CONCURRENTLY stats_test_idx1;
 -- false for previous oid
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  f
@@ -1212,7 +1212,7 @@ SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
 
 -- true for new oid
 SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  t
@@ -1220,7 +1220,7 @@ SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
 
 -- pg_stat_have_stats returns true for a rolled back drop index with stats
 BEGIN;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  t
@@ -1228,7 +1228,7 @@ SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
 
 DROP index stats_test_idx1;
 ROLLBACK;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
  pg_stat_have_stats 
 --------------------
  t
@@ -1513,7 +1513,7 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 (1 row)
 
 -- Test IO stats reset
-SELECT pg_stat_have_stats('io', 0, 0);
+SELECT pg_stat_have_stats('io', 0, 0, 0);
  pg_stat_have_stats 
 --------------------
  t
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index d8ac0d06f4..5a40779989 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -539,12 +539,12 @@ ROLLBACK;
 -- pg_stat_have_stats behavior
 ----
 -- fixed-numbered stats exist
-SELECT pg_stat_have_stats('bgwriter', 0, 0);
+SELECT pg_stat_have_stats('bgwriter', 0, 0, 0);
 -- unknown stats kinds error out
-SELECT pg_stat_have_stats('zaphod', 0, 0);
+SELECT pg_stat_have_stats('zaphod', 0, 0, 0);
 -- db stats have objoid 0
-SELECT pg_stat_have_stats('database', :dboid, 1);
-SELECT pg_stat_have_stats('database', :dboid, 0);
+SELECT pg_stat_have_stats('database', :dboid, 1, 0);
+SELECT pg_stat_have_stats('database', :dboid, 0, 0);
 
 -- pg_stat_have_stats returns true for committed index creation
 CREATE table stats_test_tab1 as select generate_series(1,10) a;
@@ -552,40 +552,40 @@ CREATE index stats_test_idx1 on stats_test_tab1(a);
 SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset
 SET enable_seqscan TO off;
 select a from stats_test_tab1 where a = 3;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 
 -- pg_stat_have_stats returns false for dropped index with stats
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 DROP index stats_test_idx1;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 
 -- pg_stat_have_stats returns false for rolled back index creation
 BEGIN;
 CREATE index stats_test_idx1 on stats_test_tab1(a);
 SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset
 select a from stats_test_tab1 where a = 3;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 ROLLBACK;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 
 -- pg_stat_have_stats returns true for reindex CONCURRENTLY
 CREATE index stats_test_idx1 on stats_test_tab1(a);
 SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset
 select a from stats_test_tab1 where a = 3;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 REINDEX index CONCURRENTLY stats_test_idx1;
 -- false for previous oid
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 -- true for new oid
 SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 
 -- pg_stat_have_stats returns true for a rolled back drop index with stats
 BEGIN;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 DROP index stats_test_idx1;
 ROLLBACK;
-SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid);
+SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid, 0);
 
 -- put enable_seqscan back to on
 SET enable_seqscan TO on;
@@ -759,7 +759,7 @@ SELECT sum(extends) AS io_sum_bulkwrite_strategy_extends_after
 SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_extends_before;
 
 -- Test IO stats reset
-SELECT pg_stat_have_stats('io', 0, 0);
+SELECT pg_stat_have_stats('io', 0, 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
 SELECT pg_stat_reset_shared('io');
diff --git a/src/test/subscription/t/026_stats.pl b/src/test/subscription/t/026_stats.pl
index fb3e5629b3..1f4ae5efd5 100644
--- a/src/test/subscription/t/026_stats.pl
+++ b/src/test/subscription/t/026_stats.pl
@@ -263,7 +263,7 @@ $node_subscriber->safe_psql($db, qq(DROP SUBSCRIPTION $sub1_name));
 
 # Subscription stats for sub1 should be gone
 is( $node_subscriber->safe_psql(
-		$db, qq(SELECT pg_stat_have_stats('subscription', 0, $sub1_oid))),
+		$db, qq(SELECT pg_stat_have_stats('subscription', 0, $sub1_oid, 0))),
 	qq(f),
 	qq(Subscription stats for subscription '$sub1_name' should be removed.));
 
@@ -282,7 +282,7 @@ DROP SUBSCRIPTION $sub2_name;
 
 # Subscription stats for sub2 should be gone
 is( $node_subscriber->safe_psql(
-		$db, qq(SELECT pg_stat_have_stats('subscription', 0, $sub2_oid))),
+		$db, qq(SELECT pg_stat_have_stats('subscription', 0, $sub2_oid, 0))),
 	qq(f),
 	qq(Subscription stats for subscription '$sub2_name' should be removed.));
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index d427a1c16a..d7385f9bfb 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2118,6 +2118,7 @@ PgStatShared_Function
 PgStatShared_HashEntry
 PgStatShared_IO
 PgStatShared_Relation
+PgStatShared_RelFileNode
 PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
-- 
2.34.1


--s7nniTiJPMRtECL3--





^ permalink  raw  reply  [nested|flat] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ 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; 71+ 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] 71+ messages in thread