agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v1] solaris: Use versioning scripts instead of -Bsymbolic
570+ messages / 3 participants
[nested] [flat]

* [PATCH v1] solaris: Use versioning scripts instead of -Bsymbolic
@ 2022-08-23 08:50  Andres Freund <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Andres Freund @ 2022-08-23 08:50 UTC (permalink / raw)

-Bsymbolic causes a lot of "ld: warning: symbol referencing errors"
warnings. It's quite easy to add the symbol versioning script, we just need a
slightly different parameter name.

Discussion: https://postgr.es/m/[email protected]
---
 src/Makefile.shlib | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/Makefile.shlib b/src/Makefile.shlib
index 2af6192f0f3..3202b2e67de 100644
--- a/src/Makefile.shlib
+++ b/src/Makefile.shlib
@@ -188,10 +188,15 @@ ifeq ($(PORTNAME), linux)
 endif
 
 ifeq ($(PORTNAME), solaris)
-  LINK.shared		= $(COMPILER) -shared -Wl,-Bsymbolic
+  LINK.shared		= $(COMPILER) -shared
   ifdef soname
     LINK.shared	+= -Wl,-soname,$(soname)
   endif
+  BUILD.exports		= ( echo '{ global:'; $(AWK) '/^[^\#]/ {printf "%s;\n",$$1}' $<; echo ' local: *; };' ) >$@
+  exports_file		= $(SHLIB_EXPORTS:%.txt=%.list)
+  ifneq (,$(exports_file))
+    LINK.shared		+= -Wl,-M$(exports_file)
+  endif
 endif
 
 ifeq ($(PORTNAME), cygwin)
-- 
2.37.0.3.g30cc8d0f14


--aym2ahtpoerge4dw--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v14 1/8] Row pattern recognition patch for raw parser.
@ 2024-02-28 13:59  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 570+ 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] 570+ messages in thread

* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 3acb2e1d2ba..74faa4f5582 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--2fxmamo6mu2qbxgv--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 51 +++++++++-----
 src/backend/storage/ipc/procarray.c         | 75 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  2 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 144 insertions(+), 27 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..58ebecf4927 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId *xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 781a471fc1d..29ba49744eb 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is o.k.
+		 * for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..f2008c6877c 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
-	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
-	 * means all transactions starting afterwards have enough information to
-	 * be decoded.  Switch to FULL_SNAPSHOT.
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * BUILDING_SNAPSHOT.  This means all transactions starting afterwards
+	 * have enough information to be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
-	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
-	 * transactions that are currently in progress have a catalog snapshot,
-	 * and all their changes have been collected.  Switch to CONSISTENT.
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * FULL_SNAPSHOT.  This means all transactions that are currently in
+	 * progress have a catalog snapshot, and all their changes have been
+	 * collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId *xids_repack;
+			int			i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..033ae68b57e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,25 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count,
+				count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId *xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2673,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int			nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2689,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2704,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2713,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2734,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2756,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2775,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2828,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2850,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..fe4dcdc3def 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,12 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--qfkt2ktdpcfeypib--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 7291b4180ab..0103bc10bd1 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--cldir6umqisr673d--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 21ab81c6f7f..42165c5552e 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--mdsv5bdgfjjj6d77--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 065316ee866..77c206ff944 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--nzintiedl6o4kcyp--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 4fd10a5e7b3..73407c383da 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 065316ee866..77c206ff944 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--nzintiedl6o4kcyp--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 140 insertions(+), 23 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 018e9f7b013..423cea26b0b 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..b02ec4e8c3e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..c785a3db59f 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 1dad125706e..c6693b93a65 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -69,10 +69,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--gwom7bl7ogtszo4k--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 7291b4180ab..0103bc10bd1 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--cldir6umqisr673d--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 21ab81c6f7f..42165c5552e 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--mdsv5bdgfjjj6d77--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 3acb2e1d2ba..74faa4f5582 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--2fxmamo6mu2qbxgv--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 51 +++++++++-----
 src/backend/storage/ipc/procarray.c         | 75 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  2 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 144 insertions(+), 27 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..58ebecf4927 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId *xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 781a471fc1d..29ba49744eb 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is o.k.
+		 * for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..f2008c6877c 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
-	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
-	 * means all transactions starting afterwards have enough information to
-	 * be decoded.  Switch to FULL_SNAPSHOT.
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * BUILDING_SNAPSHOT.  This means all transactions starting afterwards
+	 * have enough information to be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
-	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
-	 * transactions that are currently in progress have a catalog snapshot,
-	 * and all their changes have been collected.  Switch to CONSISTENT.
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * FULL_SNAPSHOT.  This means all transactions that are currently in
+	 * progress have a catalog snapshot, and all their changes have been
+	 * collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId *xids_repack;
+			int			i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..033ae68b57e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,25 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count,
+				count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId *xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2673,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int			nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2689,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2704,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2713,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2734,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2756,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2775,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2828,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2850,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..fe4dcdc3def 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,12 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--qfkt2ktdpcfeypib--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 4fd10a5e7b3..73407c383da 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 065316ee866..77c206ff944 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--nzintiedl6o4kcyp--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 140 insertions(+), 23 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 018e9f7b013..423cea26b0b 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..b02ec4e8c3e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..c785a3db59f 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 1dad125706e..c6693b93a65 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -69,10 +69,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--gwom7bl7ogtszo4k--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 7291b4180ab..0103bc10bd1 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--cldir6umqisr673d--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 21ab81c6f7f..42165c5552e 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--mdsv5bdgfjjj6d77--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 3acb2e1d2ba..74faa4f5582 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--2fxmamo6mu2qbxgv--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 51 +++++++++-----
 src/backend/storage/ipc/procarray.c         | 75 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  2 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 144 insertions(+), 27 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..58ebecf4927 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId *xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 781a471fc1d..29ba49744eb 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is o.k.
+		 * for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..f2008c6877c 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
-	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
-	 * means all transactions starting afterwards have enough information to
-	 * be decoded.  Switch to FULL_SNAPSHOT.
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * BUILDING_SNAPSHOT.  This means all transactions starting afterwards
+	 * have enough information to be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
-	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
-	 * transactions that are currently in progress have a catalog snapshot,
-	 * and all their changes have been collected.  Switch to CONSISTENT.
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * FULL_SNAPSHOT.  This means all transactions that are currently in
+	 * progress have a catalog snapshot, and all their changes have been
+	 * collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId *xids_repack;
+			int			i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..033ae68b57e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,25 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count,
+				count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId *xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2673,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int			nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2689,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2704,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2713,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2734,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2756,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2775,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2828,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2850,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..fe4dcdc3def 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,12 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--qfkt2ktdpcfeypib--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 51 +++++++++-----
 src/backend/storage/ipc/procarray.c         | 75 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  2 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 144 insertions(+), 27 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..58ebecf4927 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId *xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 274ad900c65..5188244dfd6 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is o.k.
+		 * for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..23511a0905a 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
-	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
-	 * means all transactions starting afterwards have enough information to
-	 * be decoded.  Switch to FULL_SNAPSHOT.
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * BUILDING_SNAPSHOT.  This means all transactions starting afterwards
+	 * have enough information to be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
-	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
-	 * transactions that are currently in progress have a catalog snapshot,
-	 * and all their changes have been collected.  Switch to CONSISTENT.
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * FULL_SNAPSHOT.  This means all transactions that are currently in
+	 * progress have a catalog snapshot, and all their changes have been
+	 * collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId *xids_repack;
+			int			i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..033ae68b57e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,25 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count,
+				count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId *xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2673,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int			nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2689,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2704,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2713,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2734,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2756,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2775,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2828,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2850,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..fe4dcdc3def 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,12 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--3n3vqr5y2jhknrqj
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v49-0007-WIP-add-max_repack_replication_slots.patch"



^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 4fd10a5e7b3..73407c383da 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 065316ee866..77c206ff944 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--nzintiedl6o4kcyp--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 140 insertions(+), 23 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 018e9f7b013..423cea26b0b 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..b02ec4e8c3e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..c785a3db59f 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 1dad125706e..c6693b93a65 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -69,10 +69,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--gwom7bl7ogtszo4k--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 7291b4180ab..0103bc10bd1 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--cldir6umqisr673d--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 21ab81c6f7f..42165c5552e 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--mdsv5bdgfjjj6d77--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 3acb2e1d2ba..74faa4f5582 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--2fxmamo6mu2qbxgv--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 51 +++++++++-----
 src/backend/storage/ipc/procarray.c         | 75 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  2 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 144 insertions(+), 27 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..58ebecf4927 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId *xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 781a471fc1d..29ba49744eb 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is o.k.
+		 * for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..f2008c6877c 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
-	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
-	 * means all transactions starting afterwards have enough information to
-	 * be decoded.  Switch to FULL_SNAPSHOT.
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * BUILDING_SNAPSHOT.  This means all transactions starting afterwards
+	 * have enough information to be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
-	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
-	 * transactions that are currently in progress have a catalog snapshot,
-	 * and all their changes have been collected.  Switch to CONSISTENT.
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * FULL_SNAPSHOT.  This means all transactions that are currently in
+	 * progress have a catalog snapshot, and all their changes have been
+	 * collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId *xids_repack;
+			int			i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..033ae68b57e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,25 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count,
+				count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId *xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2673,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int			nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2689,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2704,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2713,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2734,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2756,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2775,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2828,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2850,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..fe4dcdc3def 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,12 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--qfkt2ktdpcfeypib--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 51 +++++++++-----
 src/backend/storage/ipc/procarray.c         | 75 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  2 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 144 insertions(+), 27 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..58ebecf4927 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId *xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..f1cbdee7618 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 274ad900c65..5188244dfd6 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is o.k.
+		 * for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..23511a0905a 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
-	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
-	 * means all transactions starting afterwards have enough information to
-	 * be decoded.  Switch to FULL_SNAPSHOT.
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * BUILDING_SNAPSHOT.  This means all transactions starting afterwards
+	 * have enough information to be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
-	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
-	 * transactions that are currently in progress have a catalog snapshot,
-	 * and all their changes have been collected.  Switch to CONSISTENT.
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts'
+	 * oldestRunningXidLogical is >= than nextXid from when we switched to
+	 * FULL_SNAPSHOT.  This means all transactions that are currently in
+	 * progress have a catalog snapshot, and all their changes have been
+	 * collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId *xids_repack;
+			int			i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..033ae68b57e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,25 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count,
+				count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId *xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2673,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int			nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2689,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2704,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2713,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2734,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2756,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2775,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2828,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2850,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..fe4dcdc3def 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,12 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--3n3vqr5y2jhknrqj
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v49-0007-WIP-add-max_repack_replication_slots.patch"



^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 4fd10a5e7b3..73407c383da 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 73 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  6 +-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..79c052d3607 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 065316ee866..77c206ff944 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 0f913897acc..f1a03e6a754 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,13 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2687,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2702,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2711,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2732,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2754,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2773,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2826,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2848,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..5c4121fcbc8 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	/* array of TransactionIds */
 	if (xlrec.xcnt > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index bf3094f0f7d..120370f459d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -67,10 +67,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index c63a4f2cc6a..0bd28e270f1 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -124,10 +124,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--nzintiedl6o4kcyp--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/cluster.c              | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/proc.h                  |  3 +-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 10 files changed, 140 insertions(+), 23 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 018e9f7b013..423cea26b0b 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..b02ec4e8c3e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index f3ad90c7c7a..c785a3db59f 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 629ac3a7d3e..1730b07810f 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11D	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 1dad125706e..c6693b93a65 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -69,10 +69,11 @@ struct XidCache
 #define		PROC_AFFECTS_ALL_HORIZONS	0x20	/* this proc's xmin must be
 												 * included in vacuum horizons
 												 * in all databases */
+#define		PROC_IN_REPACK				0x40	/* currently REPACK (CONCURRENTLY) */
 
 /* flags reset at EOXact */
 #define		PROC_VACUUM_STATE_MASK \
-	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND)
+	(PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK)
 
 /*
  * Xmin-related flags. Make sure any flags that affect how the process' Xmin
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--gwom7bl7ogtszo4k--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread

* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY).
@ 2026-03-17 19:22  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 570+ messages in thread

From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw)

During logical decoding, we need to know if particular transaction performed
catalog changes because catalog information is needed to construct heap
tuples. To be sure that we have enough information of each transaction, the
logical decoding cannot start before all the already running transactions have
completed.

The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes
WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY)
and tries to setup the logical decoding, it has to wait for the completion of
all the other transactions involved in REPACK (CONCURRENTLY).

However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant
to logical decoding, so the other backends executing this command can ignore
it. This patch implements it by adding information about transactions
executing the command to the xl_running_xacts WAL record, and by teaching the
snapshot builder to use the information.
---
 src/backend/access/rmgrdesc/standbydesc.c   | 15 ++++-
 src/backend/access/transam/xlog.c           |  2 +
 src/backend/commands/repack.c               | 16 +++++
 src/backend/replication/logical/snapbuild.c | 38 ++++++++---
 src/backend/storage/ipc/procarray.c         | 74 +++++++++++++++++++--
 src/backend/storage/ipc/standby.c           |  8 ++-
 src/include/storage/standby.h               |  3 +
 src/include/storage/standbydefs.h           |  2 +
 8 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..b96b73d51d3 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 {
 	int			i;
 
-	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u",
+	appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u",
 					 xlrec->nextXid,
 					 xlrec->latestCompletedXid,
-					 xlrec->oldestRunningXid);
+					 xlrec->oldestRunningXid,
+					 xlrec->oldestRunningXidLogical);
 	if (xlrec->xcnt > 0)
 	{
 		appendStringInfo(buf, "; %d xacts:", xlrec->xcnt);
@@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	if (xlrec->xcnt_repack > 0)
+	{
+		TransactionId	*xids_repack;
+
+		appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack);
+		xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt;
+		for (i = 0; i < xlrec->xcnt_repack; i++)
+			appendStringInfo(buf, " %u", xids_repack[i]);
+	}
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f5c9a34374d..d050b0b1444 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5912,6 +5912,7 @@ StartupXLOG(void)
 				 * subxids are listed with their parent prepared transactions.
 				 */
 				running.xcnt = nxids;
+				running.xcnt_repack = 0;
 				running.subxcnt = 0;
 				running.subxid_status = SUBXIDS_IN_SUBTRANS;
 				running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
@@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record)
 			 * with their parent prepared transactions.
 			 */
 			running.xcnt = nxids;
+			running.xcnt_repack = 0;
 			running.subxcnt = 0;
 			running.subxid_status = SUBXIDS_IN_SUBTRANS;
 			running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 7291b4180ab..0103bc10bd1 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose,
 
 	if (concurrent)
 	{
+		/*
+		 * Do not let other backends wait for our completion during their
+		 * setup of logical replication. Unlike logical replication publisher,
+		 * we will have XID assigned, so the other backends - whether
+		 * walsenders involved in logical replication or regular backends
+		 * executing also REPACK (CONCURRENTLY) - would have to wait for our
+		 * completion before they can build their initial snapshot. It is
+		 * o.k. for any decoding backend to ignore us because we do not change
+		 * tuple descriptor of any table, and the data changes we write should
+		 * not be decoded by other backends.
+		 */
+		LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+		MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK;
+		ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
+		LWLockRelease(ProcArrayLock);
+
 		/*
 		 * The worker needs to be member of the locking group we're the leader
 		 * of. We ought to become the leader before the worker starts. The
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 9cf499ce7c6..fbdd4600a2b 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	builder->xmin = running->oldestRunningXidLogical;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
 	if (xmin == InvalidTransactionId)
-		xmin = running->oldestRunningXid;
+		xmin = running->oldestRunningXidLogical;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
-		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
+		 builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin);
 	LogicalIncreaseXminForSlot(lsn, xmin);
 
 	/*
@@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * have all necessary catalog rows anymore.
 	 */
 	if (TransactionIdIsNormal(builder->initial_xmin_horizon) &&
-		NormalTransactionIdPrecedes(running->oldestRunningXid,
+		NormalTransactionIdPrecedes(running->oldestRunningXidLogical,
 									builder->initial_xmin_horizon))
 	{
 		ereport(DEBUG1,
 				errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low",
 								LSN_FORMAT_ARGS(lsn)),
 				errdetail_internal("initial xmin horizon of %u vs the snapshot's %u",
-								   builder->initial_xmin_horizon, running->oldestRunningXid));
+								   builder->initial_xmin_horizon, running->oldestRunningXidLogical));
 
 
 		SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon);
@@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * NB: We might have already started to incrementally assemble a snapshot,
 	 * so we need to be careful to deal with that.
 	 */
-	if (running->oldestRunningXid == running->nextXid)
+	if (running->oldestRunningXidLogical == running->nextXid)
 	{
 		if (!XLogRecPtrIsValid(builder->start_decoding_at) ||
 			builder->start_decoding_at <= lsn)
@@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT.
 	 *
-	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid
+	 * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical
 	 * is >= than nextXid from when we switched to BUILDING_SNAPSHOT.  This
 	 * means all transactions starting afterwards have enough information to
 	 * be decoded.  Switch to FULL_SNAPSHOT.
 	 */
 	else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_FULL_SNAPSHOT;
 		builder->next_phase_at = running->nextXid;
@@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	/*
 	 * c) transition from FULL_SNAPSHOT to CONSISTENT.
 	 *
-	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is
+	 * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is
 	 * >= than nextXid from when we switched to FULL_SNAPSHOT.  This means all
 	 * transactions that are currently in progress have a catalog snapshot,
 	 * and all their changes have been collected.  Switch to CONSISTENT.
 	 */
 	else if (builder->state == SNAPBUILD_FULL_SNAPSHOT &&
 			 TransactionIdPrecedesOrEquals(builder->next_phase_at,
-										   running->oldestRunningXid))
+										   running->oldestRunningXidLogical))
 	{
 		builder->state = SNAPBUILD_CONSISTENT;
 		builder->next_phase_at = InvalidTransactionId;
@@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 		if (TransactionIdFollows(xid, cutoff))
 			continue;
 
+		/* Do not wait for transactions running REPACK (CONCURRENTLY). */
+		if (running->xcnt_repack > 0)
+		{
+			TransactionId	*xids_repack;
+			int		i;
+
+			xids_repack = running->xids + running->xcnt + running->subxcnt;
+
+			for (i = 0; i < running->xcnt_repack; i++)
+			{
+				if (xid == xids_repack[i])
+					break;
+			}
+			/* Found? */
+			if (i < running->xcnt_repack)
+				continue;
+		}
+
 		XactLockTableWait(xid, NULL, NULL, XLTW_None);
 	}
 
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..6dd4fa7dcc0 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2643,15 +2643,24 @@ GetRunningTransactionData(void)
 	RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData;
 	TransactionId latestCompletedXid;
 	TransactionId oldestRunningXid;
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid;
 	TransactionId *xids;
 	int			index;
-	int			count;
+	int			count, count_repack;
 	int			subcount;
 	bool		suboverflowed;
+	TransactionId	*xids_repack = NULL;
+	bool		logical_decoding_enabled = IsLogicalDecodingEnabled();
 
 	Assert(!RecoveryInProgress());
 
+	/*
+	 * TODO Consider a GUC to reserve certain amount of replication slots for
+	 * REPACK (CONCURRENTLY) and using it here.
+	 */
+#define		MAX_REPACK_XIDS		16
+
 	/*
 	 * Allocating space for maxProcs xids is usually overkill; numProcs would
 	 * be sufficient.  But it seems better to do the malloc while not holding
@@ -2663,11 +2672,14 @@ GetRunningTransactionData(void)
 	 */
 	if (CurrentRunningXacts->xids == NULL)
 	{
+		/* FIXME probably fails if logical decoding is enable on-the-fly */
+		int		nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0;
+
 		/*
 		 * First call
 		 */
 		CurrentRunningXacts->xids = (TransactionId *)
-			malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId));
+			malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId));
 		if (CurrentRunningXacts->xids == NULL)
 			ereport(ERROR,
 					(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -2676,7 +2688,10 @@ GetRunningTransactionData(void)
 
 	xids = CurrentRunningXacts->xids;
 
-	count = subcount = 0;
+	if (logical_decoding_enabled)
+		xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS);
+
+	count = subcount = count_repack = 0;
 	suboverflowed = false;
 
 	/*
@@ -2688,7 +2703,7 @@ GetRunningTransactionData(void)
 
 	latestCompletedXid =
 		XidFromFullTransactionId(TransamVariables->latestCompletedXid);
-	oldestDatabaseRunningXid = oldestRunningXid =
+	oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical =
 		XidFromFullTransactionId(TransamVariables->nextXid);
 
 	/*
@@ -2697,6 +2712,8 @@ GetRunningTransactionData(void)
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
 		TransactionId xid;
+		int			pgprocno;
+		PGPROC	   *proc;
 
 		/* Fetch xid just once - see GetNewTransactionId */
 		xid = UINT32_ACCESS_ONCE(other_xids[index]);
@@ -2716,6 +2733,21 @@ GetRunningTransactionData(void)
 		if (TransactionIdPrecedes(xid, oldestRunningXid))
 			oldestRunningXid = xid;
 
+		if (logical_decoding_enabled &&
+			TransactionIdPrecedes(xid, oldestRunningXidLogical))
+		{
+			/*
+			 * Backends running REPACK concurrently need to be excluded from
+			 * oldestRunningXidLogical, otherwise the snapshot builder cannot
+			 * proceed in building the initial snapshot.
+			 */
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0)
+				oldestRunningXidLogical = xid;
+		}
+
 		/*
 		 * Also, update the oldest running xid within the current database. As
 		 * fetching pgprocno and PGPROC could cause cache misses, we do cheap
@@ -2723,8 +2755,8 @@ GetRunningTransactionData(void)
 		 */
 		if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid))
 		{
-			int			pgprocno = arrayP->pgprocnos[index];
-			PGPROC	   *proc = &allProcs[pgprocno];
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
 
 			if (proc->databaseId == MyDatabaseId)
 				oldestDatabaseRunningXid = xid;
@@ -2742,6 +2774,19 @@ GetRunningTransactionData(void)
 		 */
 
 		xids[count++] = xid;
+
+		/*
+		 * Collect XIDSs of transactions running REPACK (CONCURRENTLY).
+		 */
+		if (logical_decoding_enabled &&
+			count_repack < MAX_REPACK_XIDS)
+		{
+			pgprocno = arrayP->pgprocnos[index];
+			proc = &allProcs[pgprocno];
+
+			if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK)
+				xids_repack[count_repack++] = xid;
+		}
 	}
 
 	/*
@@ -2782,6 +2827,19 @@ GetRunningTransactionData(void)
 		}
 	}
 
+	/*
+	 * Append the XIDs running REPACK (CONCURRENTLY), if any.
+	 *
+	 * XXX Should we sort the array and use bsearch() when using it?
+	 */
+	if (count_repack > 0)
+	{
+		for (int i = 0; i < count_repack; i++)
+			xids[count++] = xids_repack[i];
+	}
+	if (xids_repack)
+		pfree(xids_repack);
+
 	/*
 	 * It's important *not* to include the limits set by slots here because
 	 * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those
@@ -2791,11 +2849,13 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
-	CurrentRunningXacts->xcnt = count - subcount;
+	CurrentRunningXacts->xcnt = count - subcount - count_repack;
 	CurrentRunningXacts->subxcnt = subcount;
+	CurrentRunningXacts->xcnt_repack = count_repack;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
 	CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid);
 	CurrentRunningXacts->oldestRunningXid = oldestRunningXid;
+	CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical;
 	CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid;
 	CurrentRunningXacts->latestCompletedXid = latestCompletedXid;
 
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..fd3e4fe31f3 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record)
 		RunningTransactionsData running;
 
 		running.xcnt = xlrec->xcnt;
+		running.xcnt_repack = xlrec->xcnt_repack;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
 		running.nextXid = xlrec->nextXid;
@@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRecPtr	recptr;
 
 	xlrec.xcnt = CurrRunningXacts->xcnt;
+	xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
 	xlrec.nextXid = CurrRunningXacts->nextXid;
 	xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid;
+	xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical;
 	xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid;
 
 	/* Header */
@@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts);
 
 	/* array of TransactionIds */
-	if (xlrec.xcnt > 0)
+	if (xlrec.xcnt + xlrec.xcnt_repack > 0)
 		XLogRegisterData(CurrRunningXacts->xids,
-						 (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
+						 (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) *
+						 sizeof(TransactionId));
 
 	recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
 
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..9e6e7b18786 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -127,10 +127,13 @@ typedef enum
 typedef struct RunningTransactionsData
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK
+								 * (CONCURRENTLY). */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId oldestDatabaseRunningXid; /* same as above, but within the
 											 * current database */
 	TransactionId latestCompletedXid;	/* so we can set xmax */
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..edad609fa9a 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -47,10 +47,12 @@ typedef struct xl_standby_locks
 typedef struct xl_running_xacts
 {
 	int			xcnt;			/* # of xact ids in xids[] */
+	int			xcnt_repack;	/* # of xacts running REPACK (CONCURRENTLY) */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
 	TransactionId nextXid;		/* xid from TransamVariables->nextXid */
 	TransactionId oldestRunningXid; /* *not* oldestXmin */
+	TransactionId oldestRunningXidLogical;
 	TransactionId latestCompletedXid;	/* so we can set xmax */
 
 	TransactionId xids[FLEXIBLE_ARRAY_MEMBER];
-- 
2.47.3


--cldir6umqisr673d--





^ permalink  raw  reply  [nested|flat] 570+ messages in thread