agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v14 1/8] Row pattern recognition patch for raw parser.
209+ messages / 2 participants
[nested] [flat]

* [PATCH v14 1/8] Row pattern recognition patch for raw parser.
@ 2024-02-28 13:59  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Tatsuo Ishii @ 2024-02-28 13:59 UTC (permalink / raw)

---
 src/backend/parser/gram.y       | 220 ++++++++++++++++++++++++++++++--
 src/include/nodes/parsenodes.h  |  67 ++++++++++
 src/include/parser/kwlist.h     |   8 ++
 src/include/parser/parse_node.h |   1 +
 4 files changed, 285 insertions(+), 11 deletions(-)

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 130f7fc7c3..4581dd81aa 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -660,6 +660,21 @@ 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.
@@ -703,7 +718,7 @@ 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
 
@@ -719,7 +734,7 @@ 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
 
@@ -732,7 +747,7 @@ 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 METHOD
+	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MEASURES MERGE METHOD
 	MINUTE_P MINVALUE MODE MONTH_P MOVE
 
 	NAME_P NAMES NATIONAL NATURAL NCHAR NEW NEXT NFC NFD NFKC NFKD NO NONE
@@ -744,8 +759,8 @@ 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
-	PLACING PLANS POLICY
+	PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD PAST
+	PATTERN_P PERMUTE PLACING PLANS POLICY
 	POSITION PRECEDING PRECISION PRESERVE PREPARE PREPARED PRIMARY
 	PRIOR PRIVILEGES PROCEDURAL PROCEDURE PROCEDURES PROGRAM PUBLICATION
 
@@ -756,12 +771,13 @@ 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 SQL_P STABLE STANDALONE_P
 	START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_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 TEMP TEMPLATE TEMPORARY TEXT_P THEN
 	TIES TIME TIMESTAMP TO TRAILING TRANSACTION TRANSFORM
@@ -867,6 +883,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %nonassoc	UNBOUNDED		/* 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
+			MEASURES AFTER INITIAL SEEK PATTERN_P
 %left		Op OPERATOR		/* multi-character ops and user-defined operators */
 %left		'+' '-'
 %left		'*' '/' '%'
@@ -15935,7 +15952,8 @@ 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);
 
@@ -15943,10 +15961,12 @@ 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;
 					$$ = n;
 				}
@@ -15970,6 +15990,31 @@ opt_partition_clause: PARTITION BY expr_list		{ $$ = $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;
+					$$->location = @1;
+				}
+		;
+
 /*
  * For frame clauses, we return a WindowDef, but only some fields are used:
  * frameOptions, startOffset, and endOffset.
@@ -16129,6 +16174,143 @@ opt_window_exclusion_clause:
 			| /*EMPTY*/				{ $$ = 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.
@@ -17257,6 +17439,7 @@ unreserved_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INLINE_P
 			| INPUT_P
 			| INSENSITIVE
@@ -17284,6 +17467,7 @@ unreserved_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINUTE_P
@@ -17326,6 +17510,9 @@ unreserved_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
+			| PATTERN_P
+			| PERMUTE
 			| PLANS
 			| POLICY
 			| PRECEDING
@@ -17376,6 +17563,7 @@ unreserved_keyword:
 			| SEARCH
 			| SECOND_P
 			| SECURITY
+			| SEEK
 			| SEQUENCE
 			| SEQUENCES
 			| SERIALIZABLE
@@ -17401,6 +17589,7 @@ unreserved_keyword:
 			| STRICT_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUPPORT
 			| SYSID
 			| SYSTEM_P
@@ -17588,6 +17777,7 @@ reserved_keyword:
 			| CURRENT_USER
 			| DEFAULT
 			| DEFERRABLE
+			| DEFINE
 			| DESC
 			| DISTINCT
 			| DO
@@ -17750,6 +17940,7 @@ bare_label_keyword:
 			| DEFAULTS
 			| DEFERRABLE
 			| DEFERRED
+			| DEFINE
 			| DEFINER
 			| DELETE_P
 			| DELIMITER
@@ -17825,6 +18016,7 @@ bare_label_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INITIALLY
 			| INLINE_P
 			| INNER_P
@@ -17874,6 +18066,7 @@ bare_label_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINVALUE
@@ -17927,6 +18120,9 @@ bare_label_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
+			| PATTERN_P
+			| PERMUTE
 			| PLACING
 			| PLANS
 			| POLICY
@@ -17983,6 +18179,7 @@ bare_label_keyword:
 			| SCROLL
 			| SEARCH
 			| SECURITY
+			| SEEK
 			| SELECT
 			| SEQUENCE
 			| SEQUENCES
@@ -18014,6 +18211,7 @@ bare_label_keyword:
 			| STRICT_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUBSTRING
 			| SUPPORT
 			| SYMMETRIC
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index baa6a97c7e..14b9d328b7 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -540,6 +540,48 @@ typedef struct SortBy
 	int			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
  *
@@ -555,6 +597,9 @@ 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 */
@@ -1476,6 +1521,11 @@ 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.
  */
@@ -1507,6 +1557,23 @@ 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 2331acac09..6b3734a865 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -128,6 +128,7 @@ 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)
@@ -212,6 +213,7 @@ 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)
@@ -265,6 +267,7 @@ 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("method", METHOD, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("minute", MINUTE_P, UNRESERVED_KEYWORD, AS_LABEL)
@@ -326,6 +329,9 @@ 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("pattern", PATTERN_P, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("permute", PERMUTE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("placing", PLACING, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plans", PLANS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("policy", POLICY, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -385,6 +391,7 @@ 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)
@@ -416,6 +423,7 @@ PG_KEYWORD("stored", STORED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("strict", STRICT_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 99d6515736..1e43cef6f4 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(Thu_Feb_29_09_19_54_2024_640)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v14-0002-Row-pattern-recognition-patch-parse-analysis.patch"



^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread

* [PATCH v1 2/2] Try to avoid a rewrite when adding a stored generated column
@ 2026-03-16 23:28  Alberto Piai <[email protected]>
  0 siblings, 0 replies; 209+ messages in thread

From: Alberto Piai @ 2026-03-16 23:28 UTC (permalink / raw)

This builds upon basic support for

... ALTER COLUMN ... ADD GENERATED ALWAYS AS (expr) STORED

If we can find a constraint which proves that the given column is
already always equal to the new generated column expression, skip the
expensive rewrite of the table.

The check constraint must use an equality operator which is mergejoinable, and
the expression must match exactly the generated column's default
expression.
---
 src/backend/catalog/pg_constraint.c       |  75 +++++++++++
 src/backend/commands/tablecmds.c          |  46 ++++---
 src/include/catalog/pg_constraint.h       |   2 +
 src/test/regress/expected/alter_table.out | 155 +++++++++++++++++++++-
 src/test/regress/sql/alter_table.sql      |  81 +++++++++++
 5 files changed, 339 insertions(+), 20 deletions(-)

diff --git a/src/backend/catalog/pg_constraint.c b/src/backend/catalog/pg_constraint.c
index b12765ae691..8f207c4a79d 100644
--- a/src/backend/catalog/pg_constraint.c
+++ b/src/backend/catalog/pg_constraint.c
@@ -17,6 +17,7 @@
 #include "access/genam.h"
 #include "access/gist.h"
 #include "access/htup_details.h"
+#include "access/relation.h"
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/catalog.h"
@@ -29,6 +30,8 @@
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
 #include "common/int.h"
+#include "nodes/nodeFuncs.h"
+#include "parser/parse_relation.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
@@ -694,6 +697,78 @@ findDomainNotNullConstraint(Oid typid)
 	return retval;
 }
 
+/*
+ * Given a relation, an attnum and a (cooked) expression, this returns true if
+ * it finds a CHECK constraint which proves that the given column is equal to
+ * the expression.
+ *
+ * The constraint must use a mergejoinable operator for the type of the column,
+ * a concept used by the planner as well to infer equivalence classes on the
+ * terms in a query (see op_mergejoinable()).
+ *
+ * The expressions are compared structurally, so they must match exactly for
+ * this check to succeed.
+ */
+bool
+findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+									const Node *target_expr)
+{
+	Relation	pg_constraint;
+	HeapTuple	conTup;
+	SysScanDesc scan;
+	ScanKeyData key;
+	bool		found = false;
+
+	pg_constraint = table_open(ConstraintRelationId, AccessShareLock);
+	ScanKeyInit(&key,
+				Anum_pg_constraint_conrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+	scan = systable_beginscan(pg_constraint, ConstraintRelidTypidNameIndexId,
+							  true, NULL, 1, &key);
+
+	while (HeapTupleIsValid(conTup = systable_getnext(scan)))
+	{
+		Form_pg_constraint con = (Form_pg_constraint) GETSTRUCT(conTup);
+		char	   *conbin;
+		Datum		val;
+		Node	   *conexpr;
+
+		if (con->contype != CONSTRAINT_CHECK)
+			continue;
+		if (!con->convalidated)
+			continue;
+
+		val = SysCacheGetAttrNotNull(CONSTROID, conTup,
+									 Anum_pg_constraint_conbin);
+		conbin = TextDatumGetCString(val);
+		conexpr = stringToNode(conbin);
+
+		if (IsA(conexpr, OpExpr))
+		{
+			OpExpr	   *op = (OpExpr *) conexpr;
+
+			if (list_length(op->args) == 2 && IsA(linitial(op->args), Var))
+			{
+				Var		   *var = (Var *) linitial(op->args);
+
+				if (var->varattno == attnum &&
+					op_mergejoinable(op->opno, exprType((Node *) var)) &&
+					equal(lsecond(op->args), target_expr))
+				{
+					found = true;
+					break;
+				}
+			}
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_constraint, AccessShareLock);
+
+	return found;
+}
+
 /*
  * Given a pg_constraint tuple for a not-null constraint, return the column
  * number it is for.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e7386e81b07..005fbf78fbf 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8863,6 +8863,7 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	NewColumnValue *newval;
 	RawColumnDefault *rawEnt;
 	Relation	pg_attribute;
+	bool		rewrite;
 
 	Assert(def->raw_expr != NULL);
 	Assert(def->cooked_expr == NULL);
@@ -8926,29 +8927,36 @@ ATExecAddGeneratedAsExprStored(AlteredTableInfo *tab,
 	/* Make above changes visible */
 	CommandCounterIncrement();
 
-	/*
-	 * Clear all the missing values if we're rewriting the table, since this
-	 * renders them pointless.
-	 */
-	RelationClearMissing(rel);
-
-	/* Make above changes visible */
-	CommandCounterIncrement();
-
-	/* Drop any pg_statistic entry for the column */
-	RemoveStatistics(RelationGetRelid(rel), attnum);
-
 	/* Build a concrete expression for the new default (generated) value */
 	defval = (Expr *) build_column_default(rel, attnum);
 	defval = expression_planner(defval);
 
-	/* Schedule a rewrite */
-	newval = palloc0_object(NewColumnValue);
-	newval->attnum = attnum;
-	newval->expr = defval;
-	newval->is_generated = true;
-	tab->newvals = lappend(tab->newvals, newval);
-	tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	rewrite = !findStructuralCheckConstraintOnAttr(RelationGetRelid(rel),
+												   attnum,
+												   (Node *) defval);
+
+	if (rewrite)
+	{
+		/*
+		 * Clear all the missing values if we're rewriting the table, since
+		 * this renders them pointless.
+		 */
+		RelationClearMissing(rel);
+
+		/* Make above changes visible */
+		CommandCounterIncrement();
+
+		/* Drop any pg_statistic entry for the column */
+		RemoveStatistics(RelationGetRelid(rel), attnum);
+
+		/* Schedule a rewrite */
+		newval = palloc0_object(NewColumnValue);
+		newval->attnum = attnum;
+		newval->expr = defval;
+		newval->is_generated = true;
+		tab->newvals = lappend(tab->newvals, newval);
+		tab->rewrite |= AT_REWRITE_DEFAULT_VAL;
+	}
 
 	InvokeObjectPostAlterHook(RelationRelationId,
 							  RelationGetRelid(rel), attnum);
diff --git a/src/include/catalog/pg_constraint.h b/src/include/catalog/pg_constraint.h
index 1b7fedf1750..7ac9e00c28b 100644
--- a/src/include/catalog/pg_constraint.h
+++ b/src/include/catalog/pg_constraint.h
@@ -266,6 +266,8 @@ extern char *ChooseConstraintName(const char *name1, const char *name2,
 extern HeapTuple findNotNullConstraintAttnum(Oid relid, AttrNumber attnum);
 extern HeapTuple findNotNullConstraint(Oid relid, const char *colname);
 extern HeapTuple findDomainNotNullConstraint(Oid typid);
+extern bool findStructuralCheckConstraintOnAttr(Oid relid, AttrNumber attnum,
+												const Node *target_expr);
 extern AttrNumber extractNotNullColumn(HeapTuple constrTup);
 extern bool AdjustNotNullInheritance(Oid relid, AttrNumber attnum, const char *new_conname,
 									 bool is_local, bool is_no_inherit, bool is_notvalid);
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 75f64628aef..4062f985c5a 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -4943,6 +4943,157 @@ select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
  t
 (1 row)
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2)) NOT VALID
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+ did_rewrite 
+-------------
+ t
+(1 row)
+
+\d+ testgen.t4
+                                                 Table "testgen.t4"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           | not null | generated always as (a * 3) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b >= (a * 2))
+Not-null constraints:
+    "t4_b_not_null" NOT NULL "b"
+
+drop table testgen.t4;
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessExclusiveLock
+(1 row)
+
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+ locktype |           mode           
+----------+--------------------------
+ relation | ShareUpdateExclusiveLock
+(1 row)
+
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+ locktype |        mode         
+----------+---------------------
+ relation | AccessShareLock
+ relation | AccessExclusiveLock
+(2 rows)
+
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+ did_skip_rewrite 
+------------------
+ t
+(1 row)
+
+\d+ testgen.t5
+                                                 Table "testgen.t5"
+ Column |  Type   | Collation | Nullable |              Default               | Storage | Stats target | Description 
+--------+---------+-----------+----------+------------------------------------+---------+--------------+-------------
+ a      | integer |           |          |                                    | plain   |              | 
+ b      | integer |           |          | generated always as (a * 2) stored | plain   |              | 
+Check constraints:
+    "chk_gen_clause" CHECK (b = (a * 2))
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
@@ -4980,8 +5131,10 @@ alter table testgen.tpart alter column b add generated always as (a * 2) stored;
 ERROR:  ALTER action ALTER COLUMN ... ADD GENERATED ALWAYS AS (...) STORED cannot be performed on relation "tpart"
 DETAIL:  This operation is not supported for partitioned tables.
 drop schema testgen cascade;
-NOTICE:  drop cascades to 4 other objects
+NOTICE:  drop cascades to 6 other objects
 DETAIL:  drop cascades to table testgen.t3
+drop cascades to table testgen.t5
+drop cascades to function testgen.gen()
 drop cascades to table testgen.t1
 drop cascades to table testgen.t2
 drop cascades to table testgen.tpart
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index d776595a6ed..821f04e8073 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -3197,6 +3197,87 @@ alter table testgen.t3 alter column b add generated always as (a * 2) stored;
 select pg_relation_filenode('testgen.idx_b') as idx_filenode_after \gset
 select :idx_filenode_before != :idx_filenode_after as did_rewrite_idx;
 
+-- turning a regular column into a stored generated column
+-- without rewriting the table (when a check constraint proves it isn't needed)
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before = :t4_filenode_after as did_skip_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint is not
+-- valid
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b = a * 2) not valid;
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 2) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- turning a regular column into a stored generated column
+-- same as the previous case, but a rewrite happens since the constraint
+-- operator is not mergejoinable
+create table testgen.t4 (a int, b int not null);
+insert into testgen.t4 (a, b) select x, x * 2 from generate_series(0, 5) x;
+alter table testgen.t4 add constraint chk_gen_clause check (b >= a * 2);
+select pg_relation_filenode('testgen.t4') as t4_filenode_before \gset
+alter table testgen.t4 alter column b add generated always as (a * 3) stored;
+select pg_relation_filenode('testgen.t4') as t4_filenode_after \gset
+select :t4_filenode_before != :t4_filenode_after as did_rewrite;
+\d+ testgen.t4
+drop table testgen.t4;
+
+-- test the whole process for adding a stored generated column without
+-- long-lived exclusive locks
+create table testgen.t5 (a int);
+select pg_relation_filenode('testgen.t5') as t5_filenode_before \gset
+insert into testgen.t5 select x from generate_series(1, 5) x;
+alter table testgen.t5 add column b int;
+-- take care of new and updated columns
+create function testgen.gen () returns trigger language plpgsql as $$
+begin
+  new.b = new.a * 2; return new;
+end
+$$;
+create trigger testgen_gen
+    before insert or update on testgen.t5
+    for each row execute function testgen.gen();
+-- add the constraint as not valid: enforced only for new and updated rows
+begin;
+alter table testgen.t5
+    add constraint chk_gen_clause check (b = a * 2) not valid;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+insert into testgen.t5 (a) values (100), (200), (300);
+-- backfill existing rows at the appropriate pace
+update testgen.t5 set b = a * 2 where b is null;
+-- validate: this scans the table, but without an exclusive lock
+begin;
+alter table testgen.t5 validate constraint chk_gen_clause;
+select locktype, mode from pg_locks
+  where relation = 'testgen.t5'::regclass and granted;
+commit;
+-- now the schema update, which skips the rewrite because of the check
+begin;
+drop trigger testgen_gen on testgen.t5;
+alter table testgen.t5 alter column b
+    add generated always as (a * 2) stored;
+select locktype, mode from pg_locks
+where relation = 'testgen.t5'::regclass and granted;
+commit;
+select pg_relation_filenode('testgen.t5') as t5_filenode_after \gset
+select :t5_filenode_before = :t5_filenode_after as did_skip_rewrite;
+\d+ testgen.t5
+
 -- tests for invalid invocations
 alter table doesnotexist alter column foo
   add generated always as (bar * 2) stored;
-- 
2.51.2


--24dzbv6kpqxe4yje--





^ permalink  raw  reply  [nested|flat] 209+ messages in thread