agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v25 1/9] Row pattern recognition patch for raw parser.
130+ messages / 4 participants
[nested] [flat]

* [PATCH v25 1/9] Row pattern recognition patch for raw parser.
@ 2024-12-21 06:19  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Tatsuo Ishii @ 2024-12-21 06:19 UTC (permalink / raw)

---
 src/backend/parser/gram.y       | 221 ++++++++++++++++++++++++++++++--
 src/include/nodes/parsenodes.h  |  67 ++++++++++
 src/include/parser/kwlist.h     |   8 ++
 src/include/parser/parse_node.h |   1 +
 4 files changed, 286 insertions(+), 11 deletions(-)

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 67eb96396a..d21dc28955 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -664,6 +664,21 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 				json_object_constructor_null_clause_opt
 				json_array_constructor_null_clause_opt
 
+%type <target>	row_pattern_measure_item
+				row_pattern_definition
+%type <node>	opt_row_pattern_common_syntax
+				opt_row_pattern_skip_to
+				row_pattern_subset_item
+				row_pattern_term
+%type <list>	opt_row_pattern_measures
+				row_pattern_measure_list
+				row_pattern_definition_list
+				opt_row_pattern_subset_clause
+				row_pattern_subset_list
+				row_pattern_subset_rhs
+				row_pattern
+%type <boolean>	opt_row_pattern_initial_or_seek
+				first_or_last
 
 /*
  * Non-keyword token types.  These are hard-wired into the "flex" lexer.
@@ -707,7 +722,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	CURRENT_TIME CURRENT_TIMESTAMP CURRENT_USER CURSOR CYCLE
 
 	DATA_P DATABASE DAY_P DEALLOCATE DEC DECIMAL_P DECLARE DEFAULT DEFAULTS
-	DEFERRABLE DEFERRED DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DEPTH DESC
+	DEFERRABLE DEFERRED DEFINE DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DEPTH DESC
 	DETACH DICTIONARY DISABLE_P DISCARD DISTINCT DO DOCUMENT_P DOMAIN_P
 	DOUBLE_P DROP
 
@@ -723,7 +738,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	HANDLER HAVING HEADER_P HOLD HOUR_P
 
 	IDENTITY_P IF_P ILIKE IMMEDIATE IMMUTABLE IMPLICIT_P IMPORT_P IN_P INCLUDE
-	INCLUDING INCREMENT INDENT INDEX INDEXES INHERIT INHERITS INITIALLY INLINE_P
+	INCLUDING INCREMENT INDENT INDEX INDEXES INHERIT INHERITS INITIAL INITIALLY INLINE_P
 	INNER_P INOUT INPUT_P INSENSITIVE INSERT INSTEAD INT_P INTEGER
 	INTERSECT INTERVAL INTO INVOKER IS ISNULL ISOLATION
 
@@ -736,7 +751,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	LEADING LEAKPROOF LEAST LEFT LEVEL LIKE LIMIT LISTEN LOAD LOCAL
 	LOCALTIME LOCALTIMESTAMP LOCATION LOCK_P LOCKED LOGGED
 
-	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MERGE MERGE_ACTION METHOD
+	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MEASURES MERGE MERGE_ACTION METHOD
 	MINUTE_P MINVALUE MODE MONTH_P MOVE
 
 	NAME_P NAMES NATIONAL NATURAL NCHAR NESTED NEW NEXT NFC NFD NFKC NFKD NO
@@ -748,8 +763,9 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	ORDER ORDINALITY OTHERS OUT_P OUTER_P
 	OVER OVERLAPS OVERLAY OVERRIDING OWNED OWNER
 
-	PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD PATH
-	PERIOD PLACING PLAN PLANS POLICY
+	PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD PAST
+	PATH PATTERN_P PERIOD PERMUTE PLACING PLAN PLANS POLICY
+
 	POSITION PRECEDING PRECISION PRESERVE PREPARE PREPARED PRIMARY
 	PRIOR PRIVILEGES PROCEDURAL PROCEDURE PROCEDURES PROGRAM PUBLICATION
 
@@ -760,12 +776,13 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
 	ROUTINE ROUTINES ROW ROWS RULE
 
-	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT
+	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SEEK SELECT
 	SEQUENCE SEQUENCES
+
 	SERIALIZABLE SERVER SESSION SESSION_USER SET SETS SETOF SHARE SHOW
 	SIMILAR SIMPLE SKIP SMALLINT SNAPSHOT SOME SOURCE SQL_P STABLE STANDALONE_P
 	START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_P STRING_P STRIP_P
-	SUBSCRIPTION SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
+	SUBSCRIPTION SUBSET SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
 
 	TABLE TABLES TABLESAMPLE TABLESPACE TARGET TEMP TEMPLATE TEMPORARY TEXT_P THEN
 	TIES TIME TIMESTAMP TO TRAILING TRANSACTION TRANSFORM
@@ -874,6 +891,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %nonassoc	UNBOUNDED NESTED /* ideally would have same precedence as IDENT */
 %nonassoc	IDENT PARTITION RANGE ROWS GROUPS PRECEDING FOLLOWING CUBE ROLLUP
 			SET KEYS OBJECT_P SCALAR VALUE_P WITH WITHOUT PATH
+			MEASURES AFTER INITIAL SEEK PATTERN_P
 %left		Op OPERATOR		/* multi-character ops and user-defined operators */
 %left		'+' '-'
 %left		'*' '/' '%'
@@ -16326,7 +16344,8 @@ over_clause: OVER window_specification
 		;
 
 window_specification: '(' opt_existing_window_name opt_partition_clause
-						opt_sort_clause opt_frame_clause ')'
+						opt_sort_clause opt_row_pattern_measures opt_frame_clause
+						opt_row_pattern_common_syntax ')'
 				{
 					WindowDef  *n = makeNode(WindowDef);
 
@@ -16334,10 +16353,12 @@ window_specification: '(' opt_existing_window_name opt_partition_clause
 					n->refname = $2;
 					n->partitionClause = $3;
 					n->orderClause = $4;
+					n->rowPatternMeasures = $5;
 					/* copy relevant fields of opt_frame_clause */
-					n->frameOptions = $5->frameOptions;
-					n->startOffset = $5->startOffset;
-					n->endOffset = $5->endOffset;
+					n->frameOptions = $6->frameOptions;
+					n->startOffset = $6->startOffset;
+					n->endOffset = $6->endOffset;
+					n->rpCommonSyntax = (RPCommonSyntax *)$7;
 					n->location = @1;
 					$$ = n;
 				}
@@ -16361,6 +16382,31 @@ opt_partition_clause: PARTITION BY expr_list		{ $$ = $3; }
 			| /*EMPTY*/								{ $$ = NIL; }
 		;
 
+/*
+ * ROW PATTERN_P MEASURES
+ */
+opt_row_pattern_measures: MEASURES row_pattern_measure_list	{ $$ = $2; }
+			| /*EMPTY*/								{ $$ = NIL; }
+		;
+
+row_pattern_measure_list:
+			row_pattern_measure_item
+					{ $$ = list_make1($1); }
+			| row_pattern_measure_list ',' row_pattern_measure_item
+					{ $$ = lappend($1, $3); }
+		;
+
+row_pattern_measure_item:
+			a_expr AS ColLabel
+				{
+					$$ = makeNode(ResTarget);
+					$$->name = $3;
+					$$->indirection = NIL;
+					$$->val = (Node *) $1;
+					$$->location = @1;
+				}
+		;
+
 /*
  * For frame clauses, we return a WindowDef, but only some fields are used:
  * frameOptions, startOffset, and endOffset.
@@ -16520,6 +16566,143 @@ opt_window_exclusion_clause:
 			| /*EMPTY*/				{ $$ = 0; }
 		;
 
+opt_row_pattern_common_syntax:
+opt_row_pattern_skip_to opt_row_pattern_initial_or_seek
+				PATTERN_P '(' row_pattern ')'
+				opt_row_pattern_subset_clause
+				DEFINE row_pattern_definition_list
+			{
+				RPCommonSyntax *n = makeNode(RPCommonSyntax);
+				n->rpSkipTo = ((RPCommonSyntax *)$1)->rpSkipTo;
+				n->rpSkipVariable = ((RPCommonSyntax *)$1)->rpSkipVariable;
+				n->initial = $2;
+				n->rpPatterns = $5;
+				n->rpSubsetClause = $7;
+				n->rpDefs = $9;
+				$$ = (Node *) n;
+			}
+			| /*EMPTY*/		{ $$ = NULL; }
+	;
+
+opt_row_pattern_skip_to:
+			AFTER MATCH SKIP TO NEXT ROW
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_NEXT_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = (Node *) n;
+			}
+			| AFTER MATCH SKIP PAST LAST_P ROW
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_PAST_LAST_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = (Node *) n;
+				}
+			| AFTER MATCH SKIP TO first_or_last ColId
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = $5? ST_FIRST_VARIABLE : ST_LAST_VARIABLE;
+					n->rpSkipVariable = $6;
+					$$ = (Node *) n;
+				}
+/*
+			| AFTER MATCH SKIP TO LAST_P ColId		%prec LAST_P
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_LAST_VARIABLE;
+					n->rpSkipVariable = $6;
+					$$ = n;
+				}
+			| AFTER MATCH SKIP TO ColId
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_VARIABLE;
+					n->rpSkipVariable = $5;
+					$$ = n;
+				}
+*/
+			| /*EMPTY*/
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					/* temporary set default to ST_NEXT_ROW */
+					n->rpSkipTo = ST_PAST_LAST_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = (Node *) n;
+				}
+	;
+
+first_or_last:
+			FIRST_P		{ $$ = true; }
+			| LAST_P	{ $$ = false; }
+	;
+
+opt_row_pattern_initial_or_seek:
+			INITIAL			{ $$ = true; }
+			| SEEK
+				{
+					ereport(ERROR,
+							(errcode(ERRCODE_SYNTAX_ERROR),
+							 errmsg("SEEK is not supported"),
+							 errhint("Use INITIAL."),
+							 parser_errposition(@1)));
+				}
+			| /*EMPTY*/		{ $$ = true; }
+		;
+
+row_pattern:
+			row_pattern_term							{ $$ = list_make1($1); }
+			| row_pattern row_pattern_term				{ $$ = lappend($1, $2); }
+		;
+
+row_pattern_term:
+			ColId	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "", (Node *)makeString($1), NULL, @1); }
+			| ColId '*'	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "*", (Node *)makeString($1), NULL, @1); }
+			| ColId '+'	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "+", (Node *)makeString($1), NULL, @1); }
+			| ColId '?'	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "?", (Node *)makeString($1), NULL, @1); }
+		;
+
+opt_row_pattern_subset_clause:
+			SUBSET row_pattern_subset_list	{ $$ = $2; }
+			| /*EMPTY*/												{ $$ = NIL; }
+		;
+
+row_pattern_subset_list:
+			row_pattern_subset_item									{ $$ = list_make1($1); }
+			| row_pattern_subset_list ',' row_pattern_subset_item	{ $$ = lappend($1, $3); }
+			| /*EMPTY*/												{ $$ = NIL; }
+		;
+
+row_pattern_subset_item: ColId '=' '(' row_pattern_subset_rhs ')'
+			{
+				RPSubsetItem *n = makeNode(RPSubsetItem);
+				n->name = $1;
+				n->rhsVariable = $4;
+				$$ = (Node *) n;
+			}
+		;
+
+row_pattern_subset_rhs:
+			ColId								{ $$ = list_make1(makeStringConst($1, @1)); }
+			| row_pattern_subset_rhs ',' ColId	{ $$ = lappend($1, makeStringConst($3, @1)); }
+			| /*EMPTY*/							{ $$ = NIL; }
+		;
+
+row_pattern_definition_list:
+			row_pattern_definition										{ $$ = list_make1($1); }
+			| row_pattern_definition_list ',' row_pattern_definition	{ $$ = lappend($1, $3); }
+		;
+
+row_pattern_definition:
+			ColId AS a_expr
+				{
+					$$ = makeNode(ResTarget);
+					$$->name = $1;
+					$$->indirection = NIL;
+					$$->val = (Node *) $3;
+					$$->location = @1;
+				}
+		;
 
 /*
  * Supporting nonterminals for expressions.
@@ -17732,6 +17915,7 @@ unreserved_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INLINE_P
 			| INPUT_P
 			| INSENSITIVE
@@ -17760,6 +17944,7 @@ unreserved_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINUTE_P
@@ -17804,8 +17989,11 @@ unreserved_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLAN
 			| PLANS
 			| POLICY
@@ -17857,6 +18045,7 @@ unreserved_keyword:
 			| SEARCH
 			| SECOND_P
 			| SECURITY
+			| SEEK
 			| SEQUENCE
 			| SEQUENCES
 			| SERIALIZABLE
@@ -17884,6 +18073,7 @@ unreserved_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUPPORT
 			| SYSID
 			| SYSTEM_P
@@ -18078,6 +18268,7 @@ reserved_keyword:
 			| CURRENT_USER
 			| DEFAULT
 			| DEFERRABLE
+			| DEFINE
 			| DESC
 			| DISTINCT
 			| DO
@@ -18241,6 +18432,7 @@ bare_label_keyword:
 			| DEFAULTS
 			| DEFERRABLE
 			| DEFERRED
+			| DEFINE
 			| DEFINER
 			| DELETE_P
 			| DELIMITER
@@ -18318,6 +18510,7 @@ bare_label_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INITIALLY
 			| INLINE_P
 			| INNER_P
@@ -18372,6 +18565,7 @@ bare_label_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| MERGE_ACTION
 			| METHOD
@@ -18428,8 +18622,11 @@ bare_label_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLACING
 			| PLAN
 			| PLANS
@@ -18487,6 +18684,7 @@ bare_label_keyword:
 			| SCROLL
 			| SEARCH
 			| SECURITY
+			| SEEK
 			| SELECT
 			| SEQUENCE
 			| SEQUENCES
@@ -18520,6 +18718,7 @@ bare_label_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUBSTRING
 			| SUPPORT
 			| SYMMETRIC
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 0f9462493e..defc62bf9b 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -552,6 +552,48 @@ typedef struct SortBy
 	ParseLoc	location;		/* operator location, or -1 if none/unknown */
 } SortBy;
 
+/*
+ * AFTER MATCH row pattern skip to types in row pattern common syntax
+ */
+typedef enum RPSkipTo
+{
+	ST_NONE,					/* AFTER MATCH omitted */
+	ST_NEXT_ROW,				/* SKIP TO NEXT ROW */
+	ST_PAST_LAST_ROW,			/* SKIP TO PAST LAST ROW */
+	ST_FIRST_VARIABLE,			/* SKIP TO FIRST variable name */
+	ST_LAST_VARIABLE,			/* SKIP TO LAST variable name */
+	ST_VARIABLE					/* SKIP TO variable name */
+} RPSkipTo;
+
+/*
+ * Row Pattern SUBSET clause item
+ */
+typedef struct RPSubsetItem
+{
+	NodeTag		type;
+	char	   *name;			/* Row Pattern SUBSET clause variable name */
+	List	   *rhsVariable;	/* Row Pattern SUBSET rhs variables (list of
+								 * char *string) */
+} RPSubsetItem;
+
+/*
+ * RowPatternCommonSyntax - raw representation of row pattern common syntax
+ *
+ */
+typedef struct RPCommonSyntax
+{
+	NodeTag		type;
+	RPSkipTo	rpSkipTo;		/* Row Pattern AFTER MATCH SKIP type */
+	char	   *rpSkipVariable; /* Row Pattern Skip To variable name, if any */
+	bool		initial;		/* true if <row pattern initial or seek> is
+								 * initial */
+	List	   *rpPatterns;		/* PATTERN variables (list of A_Expr) */
+	List	   *rpSubsetClause; /* row pattern subset clause (list of
+								 * RPSubsetItem), if any */
+	List	   *rpDefs;			/* row pattern definitions clause (list of
+								 * ResTarget) */
+} RPCommonSyntax;
+
 /*
  * WindowDef - raw representation of WINDOW and OVER clauses
  *
@@ -567,6 +609,9 @@ typedef struct WindowDef
 	char	   *refname;		/* referenced window name, if any */
 	List	   *partitionClause;	/* PARTITION BY expression list */
 	List	   *orderClause;	/* ORDER BY (list of SortBy) */
+	List	   *rowPatternMeasures; /* row pattern measures (list of
+									 * ResTarget) */
+	RPCommonSyntax *rpCommonSyntax; /* row pattern common syntax */
 	int			frameOptions;	/* frame_clause options, see below */
 	Node	   *startOffset;	/* expression for starting bound, if any */
 	Node	   *endOffset;		/* expression for ending bound, if any */
@@ -1530,6 +1575,11 @@ typedef struct GroupingSet
  * the orderClause might or might not be copied (see copiedOrder); the framing
  * options are never copied, per spec.
  *
+ * "defineClause" is Row Pattern Recognition DEFINE clause (list of
+ * TargetEntry). TargetEntry.resname represents row pattern definition
+ * variable name. "patternVariable" and "patternRegexp" represents PATTERN
+ * clause.
+ *
  * The information relevant for the query jumbling is the partition clause
  * type and its bounds.
  */
@@ -1559,6 +1609,23 @@ typedef struct WindowClause
 	Index		winref;			/* ID referenced by window functions */
 	/* did we copy orderClause from refname? */
 	bool		copiedOrder pg_node_attr(query_jumble_ignore);
+	/* Row Pattern AFTER MACH SKIP clause */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */
+	char	   *rpSkipVariable; /* Row Pattern Skip To variable */
+	bool		initial;		/* true if <row pattern initial or seek> is
+								 * initial */
+	/* Row Pattern DEFINE clause (list of TargetEntry) */
+	List	   *defineClause;
+	/* Row Pattern DEFINE variable initial names (list of String) */
+	List	   *defineInitial;
+	/* Row Pattern PATTERN variable name (list of String) */
+	List	   *patternVariable;
+
+	/*
+	 * Row Pattern PATTERN regular expression quantifier ('+' or ''. list of
+	 * String)
+	 */
+	List	   *patternRegexp;
 } WindowClause;
 
 /*
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index 899d64ad55..f52d797615 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -129,6 +129,7 @@ PG_KEYWORD("default", DEFAULT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("defaults", DEFAULTS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferrable", DEFERRABLE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferred", DEFERRED, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("define", DEFINE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("definer", DEFINER, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delete", DELETE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delimiter", DELIMITER, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -215,6 +216,7 @@ PG_KEYWORD("index", INDEX, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("indexes", INDEXES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherit", INHERIT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherits", INHERITS, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("initial", INITIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("initially", INITIALLY, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inline", INLINE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inner", INNER_P, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL)
@@ -273,6 +275,7 @@ PG_KEYWORD("match", MATCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("matched", MATCHED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("materialized", MATERIALIZED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("maxvalue", MAXVALUE, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("measures", MEASURES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge", MERGE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge_action", MERGE_ACTION, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("method", METHOD, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -337,8 +340,11 @@ PG_KEYWORD("partial", PARTIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("partition", PARTITION, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("passing", PASSING, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("password", PASSWORD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("past", PAST, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("path", PATH, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("pattern", PATTERN_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("period", PERIOD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("permute", PERMUTE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("placing", PLACING, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plan", PLAN, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plans", PLANS, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -399,6 +405,7 @@ PG_KEYWORD("scroll", SCROLL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("search", SEARCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("second", SECOND_P, UNRESERVED_KEYWORD, AS_LABEL)
 PG_KEYWORD("security", SECURITY, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("seek", SEEK, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("select", SELECT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequence", SEQUENCE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequences", SEQUENCES, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -432,6 +439,7 @@ PG_KEYWORD("strict", STRICT_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("string", STRING_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("strip", STRIP_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("subscription", SUBSCRIPTION, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("subset", SUBSET, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("substring", SUBSTRING, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("support", SUPPORT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("symmetric", SYMMETRIC, RESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h
index 2375e95c10..737f8a9e0e 100644
--- a/src/include/parser/parse_node.h
+++ b/src/include/parser/parse_node.h
@@ -51,6 +51,7 @@ typedef enum ParseExprKind
 	EXPR_KIND_WINDOW_FRAME_RANGE,	/* window frame clause with RANGE */
 	EXPR_KIND_WINDOW_FRAME_ROWS,	/* window frame clause with ROWS */
 	EXPR_KIND_WINDOW_FRAME_GROUPS,	/* window frame clause with GROUPS */
+	EXPR_KIND_RPR_DEFINE,		/* DEFINE */
 	EXPR_KIND_SELECT_TARGET,	/* SELECT target list item */
 	EXPR_KIND_INSERT_TARGET,	/* INSERT target list item */
 	EXPR_KIND_UPDATE_SOURCE,	/* UPDATE assignment source item */
-- 
2.25.1


----Next_Part(Sat_Dec_21_18_20_04_2024_526)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v25-0002-Row-pattern-recognition-patch-parse-analysis.patch"



^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread

* [PATCH] Add hook for plugins to acquire sample rows during ANALYZE
@ 2026-05-29 12:35  Samba Siva <[email protected]>
  0 siblings, 0 replies; 130+ messages in thread

From: Samba Siva @ 2026-05-29 12:35 UTC (permalink / raw)

- Introduced AcquireSampleRowsFunc_hook for extensions to override row sampling.
- Updated analyze.c to utilize the hook if registered.
- Added tests to ensure ANALYZE completes without errors with the new hook.
---
 doc/src/sgml/xfunc.sgml               | 10 ++++++++++
 src/backend/commands/analyze.c        | 24 ++++++++++++++++++++----
 src/include/commands/vacuum.h         | 11 +++++++++++
 src/test/regress/expected/analyze.out | 20 ++++++++++++++++++++
 src/test/regress/parallel_schedule    |  1 +
 src/test/regress/sql/analyze.sql      | 24 ++++++++++++++++++++++++
 6 files changed, 86 insertions(+), 4 deletions(-)
 create mode 100644 src/test/regress/expected/analyze.out
 create mode 100644 src/test/regress/sql/analyze.sql

diff --git a/doc/src/sgml/xfunc.sgml b/doc/src/sgml/xfunc.sgml
index 1eb5abffd8..f1ef025ae2 100644
--- a/doc/src/sgml/xfunc.sgml
+++ b/doc/src/sgml/xfunc.sgml
@@ -4203,4 +4203,14 @@ supportfn(internal) returns internal
     To create such conditions, the support function must implement
     the <literal>SupportRequestIndexCondition</literal> request type.
    </para>
+
+   <para>
+    The hook variable <varname>AcquireSampleRowsFunc_hook</varname> allows extensions
+    to override the row sampling function during <command>ANALYZE</command> for regular
+    heap relations. This is useful for extensions/systems which implement distributed
+    databases and want to sample rows from remote nodes instead of the local heap.
+    The hook function fills the provided <literal>rows[]</literal> buffer with at most
+    <literal>targrows</literal> heap tuples and sets <literal>*totalrows</literal> to the
+    estimated total live row count of the relation.
+   </para>
   </sect1>
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 4fffb76e55..3560acdff1 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -74,6 +74,8 @@ int			default_statistics_target = 100;
 static MemoryContext anl_context = NULL;
 static BufferAccessStrategy vac_strategy;
 
+/* Hook for plugins to acquire sample rows for ANALYZE */
+AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook = NULL;
 
 static void do_analyze_rel(Relation onerel,
 						   VacuumParams *params, List *va_cols,
@@ -188,8 +190,15 @@ analyze_rel(Oid relid, RangeVar *relation,
 	if (onerel->rd_rel->relkind == RELKIND_RELATION ||
 		onerel->rd_rel->relkind == RELKIND_MATVIEW)
 	{
-		/* Regular table, so we'll use the regular row acquisition function */
-		acquirefunc = acquire_sample_rows;
+		/*
+		 * Regular table, so we'll use the regular row acquisition function.
+		 * If a plugin has registered a hook to acquire sample rows, use it;
+		 * otherwise use the default function.
+		 */
+		if (AcquireSampleRowsFunc_hook)
+			acquirefunc = AcquireSampleRowsFunc_hook;
+		else
+			acquirefunc = acquire_sample_rows;
 		/* Also get regular table's size */
 		relpages = RelationGetNumberOfBlocks(onerel);
 	}
@@ -1467,8 +1476,15 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		if (childrel->rd_rel->relkind == RELKIND_RELATION ||
 			childrel->rd_rel->relkind == RELKIND_MATVIEW)
 		{
-			/* Regular table, so use the regular row acquisition function */
-			acquirefunc = acquire_sample_rows;
+			/*
+			 * Regular table, so use the regular row acquisition function.
+			 * If a plugin has registered a hook to acquire sample rows, use it;
+			 * otherwise use the default function.
+			 */
+			if (AcquireSampleRowsFunc_hook)
+				acquirefunc = AcquireSampleRowsFunc_hook;
+			else
+				acquirefunc = acquire_sample_rows;
 			relpages = RelationGetNumberOfBlocks(childrel);
 		}
 		else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bc37a80dc7..146f936861 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -21,6 +21,7 @@
 #include "catalog/pg_class.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_type.h"
+#include "foreign/fdwapi.h"
 #include "parser/parse_node.h"
 #include "storage/buf.h"
 #include "storage/lock.h"
@@ -113,6 +114,9 @@ typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
 											 int samplerows,
 											 double totalrows);
 
+/* Hook type for plugins to acquire sample rows for ANALYZE */
+typedef AcquireSampleRowsFunc AcquireSampleRowsFunc_hook_type;
+
 typedef struct VacAttrStats
 {
 	/*
@@ -334,6 +338,13 @@ extern PGDLLIMPORT int vacuum_cost_limit;
 
 extern PGDLLIMPORT int64 parallel_vacuum_worker_delay_ns;
 
+/*
+ * Hook for plugins to override row sampling during ANALYZE.
+ * Also applies to child relations of partitioned/inherited tables.
+ * See acquire_sample_rows() in src/backend/commands/analyze.c.
+ */
+extern PGDLLIMPORT AcquireSampleRowsFunc_hook_type AcquireSampleRowsFunc_hook;
+
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
 extern void vacuum(List *relations, VacuumParams *params,
diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out
new file mode 100644
index 0000000000..5bb6bbc45b
--- /dev/null
+++ b/src/test/regress/expected/analyze.out
@@ -0,0 +1,20 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+-- Should complete without error
+ANALYZE employees;
+DROP TABLE employees;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index e1e0c54019..71978ef858 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -94,6 +94,7 @@ test: vacuum_parallel
 # Run this alone, because concurrent DROP TABLE would make non-superuser
 # "ANALYZE;" fail with "relation with OID $n does not exist".
 test: maintain_every
+test: analyze
 
 # no relation related tests can be put in this group
 test: publication subscription
diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql
new file mode 100644
index 0000000000..e0bc84e9f9
--- /dev/null
+++ b/src/test/regress/sql/analyze.sql
@@ -0,0 +1,24 @@
+-- Test AcquireSampleRowsFunc_hook
+-- Usually this would be tested via a C extension.
+-- Here we just confirm this does not break the existing ANALYZE code
+-- by verifying that ANALYZE completes without error.
+
+CREATE TABLE employees (
+    id SERIAL PRIMARY KEY,
+    name TEXT,
+    department TEXT,
+    salary NUMERIC
+);
+
+INSERT INTO employees 
+    SELECT
+        i,
+        'Employee ' || i,
+        'Department ' || (i % 5),
+        (i % 100) * 1000 + 50000
+    FROM generate_series(1, 1000) i;
+
+-- Should complete without error
+ANALYZE employees;
+
+DROP TABLE employees;
-- 
2.50.1 (Apple Git-155)


------=_Part_741589_445982825.1782438414800--






^ permalink  raw  reply  [nested|flat] 130+ messages in thread