agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v47 5/9] Use BulkInsertState when copying data to the new heap.
75+ messages / 4 participants
[nested] [flat]

* [PATCH v47 5/9] Use BulkInsertState when copying data to the new heap.
@ 2026-03-11 14:20  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 75+ messages in thread

From: Antonin Houska @ 2026-03-11 14:20 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index df12117236a..f6bfb282489 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -51,6 +51,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -708,6 +713,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -743,6 +749,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -974,8 +982,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1023,10 +1035,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1038,6 +1055,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2430,56 +2449,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0006-rename-cluster.c-h-to-repack.c-h.patch"



^ permalink  raw  reply  [nested|flat] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ 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; 75+ 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] 75+ messages in thread