agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v18 1/8] Row pattern recognition patch for raw parser.
416+ messages / 2 participants
[nested] [flat]

* [PATCH v18 1/8] Row pattern recognition patch for raw parser.
@ 2024-05-11 07:11  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Tatsuo Ishii @ 2024-05-11 07:11 UTC (permalink / raw)

---
 src/backend/parser/gram.y       | 221 ++++++++++++++++++++++++++++++--
 src/include/nodes/parsenodes.h  |  67 ++++++++++
 src/include/parser/kwlist.h     |   8 ++
 src/include/parser/parse_node.h |   1 +
 4 files changed, 285 insertions(+), 12 deletions(-)

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index e8b619926e..c09a0f7e4f 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -680,6 +680,21 @@ 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.
@@ -723,7 +738,7 @@ 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
 
@@ -739,7 +754,7 @@ 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
 
@@ -752,7 +767,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	LEADING LEAKPROOF LEAST LEFT LEVEL LIKE LIMIT LISTEN LOAD LOCAL
 	LOCALTIME LOCALTIMESTAMP LOCATION LOCK_P LOCKED LOGGED
 
-	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MERGE MERGE_ACTION METHOD
+	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MEASURES MERGE MERGE_ACTION METHOD
 	MINUTE_P MINVALUE MODE MONTH_P MOVE
 
 	NAME_P NAMES NATIONAL NATURAL NCHAR NESTED NEW NEXT NFC NFD NFKC NFKD NO
@@ -764,9 +779,8 @@ 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 PARTITIONS PASSING PASSWORD PATH
-	PERIOD PLACING PLAN PLANS POLICY
-
+	PARALLEL PARAMETER PARSER PARTIAL PARTITION PARTITIONS PASSING PASSWORD PAST
+	PATH PATTERN_P PERIOD PERMUTE PLACING PLAN PLANS POLICY
 	POSITION PRECEDING PRECISION PRESERVE PREPARE PREPARED PRIMARY
 	PRIOR PRIVILEGES PROCEDURAL PROCEDURE PROCEDURES PROGRAM PUBLICATION
 
@@ -777,12 +791,13 @@ 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 SPLIT SOURCE SQL_P STABLE STANDALONE_P
 	START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_P STRING_P STRIP_P
-	SUBSCRIPTION SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
+	SUBSCRIPTION SUBSET SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
 
 	TABLE TABLES TABLESAMPLE TABLESPACE TARGET TEMP TEMPLATE TEMPORARY TEXT_P THEN
 	TIES TIME TIMESTAMP TO TRAILING TRANSACTION TRANSFORM
@@ -891,6 +906,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %nonassoc	UNBOUNDED NESTED /* ideally would have same precedence as IDENT */
 %nonassoc	IDENT PARTITION RANGE ROWS GROUPS PRECEDING FOLLOWING CUBE ROLLUP
 			SET KEYS OBJECT_P SCALAR VALUE_P WITH WITHOUT PATH
+			MEASURES AFTER INITIAL SEEK PATTERN_P
 %left		Op OPERATOR		/* multi-character ops and user-defined operators */
 %left		'+' '-'
 %left		'*' '/' '%'
@@ -16333,7 +16349,8 @@ 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);
 
@@ -16341,10 +16358,12 @@ 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;
 					$$ = n;
 				}
@@ -16368,6 +16387,31 @@ opt_partition_clause: PARTITION BY expr_list		{ $$ = $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;
+					$$->location = @1;
+				}
+		;
+
 /*
  * For frame clauses, we return a WindowDef, but only some fields are used:
  * frameOptions, startOffset, and endOffset.
@@ -16527,6 +16571,143 @@ opt_window_exclusion_clause:
 			| /*EMPTY*/				{ $$ = 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.
@@ -17737,6 +17918,7 @@ unreserved_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INLINE_P
 			| INPUT_P
 			| INSENSITIVE
@@ -17765,6 +17947,7 @@ unreserved_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINUTE_P
@@ -17810,8 +17993,11 @@ unreserved_keyword:
 			| PARTITIONS
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLAN
 			| PLANS
 			| POLICY
@@ -17864,6 +18050,7 @@ unreserved_keyword:
 			| SEARCH
 			| SECOND_P
 			| SECURITY
+			| SEEK
 			| SEQUENCE
 			| SEQUENCES
 			| SERIALIZABLE
@@ -17892,6 +18079,7 @@ unreserved_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUPPORT
 			| SYSID
 			| SYSTEM_P
@@ -18086,6 +18274,7 @@ reserved_keyword:
 			| CURRENT_USER
 			| DEFAULT
 			| DEFERRABLE
+			| DEFINE
 			| DESC
 			| DISTINCT
 			| DO
@@ -18249,6 +18438,7 @@ bare_label_keyword:
 			| DEFAULTS
 			| DEFERRABLE
 			| DEFERRED
+			| DEFINE
 			| DEFINER
 			| DELETE_P
 			| DELIMITER
@@ -18326,6 +18516,7 @@ bare_label_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INITIALLY
 			| INLINE_P
 			| INNER_P
@@ -18380,6 +18571,7 @@ bare_label_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| MERGE_ACTION
 			| METHOD
@@ -18437,8 +18629,11 @@ bare_label_keyword:
 			| PARTITIONS
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLACING
 			| PLAN
 			| PLANS
@@ -18497,6 +18692,7 @@ bare_label_keyword:
 			| SCROLL
 			| SEARCH
 			| SECURITY
+			| SEEK
 			| SELECT
 			| SEQUENCE
 			| SEQUENCES
@@ -18531,6 +18727,7 @@ bare_label_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUBSTRING
 			| SUPPORT
 			| SYMMETRIC
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 3ca06fc3af..9e65e9132c 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -550,6 +550,48 @@ typedef struct SortBy
 	ParseLoc	location;		/* operator location, or -1 if none/unknown */
 } SortBy;
 
+/*
+ * AFTER MATCH row pattern skip to types in row pattern common syntax
+ */
+typedef enum RPSkipTo
+{
+	ST_NONE,					/* AFTER MATCH omitted */
+	ST_NEXT_ROW,				/* SKIP TO NEXT ROW */
+	ST_PAST_LAST_ROW,			/* SKIP TO PAST LAST ROW */
+	ST_FIRST_VARIABLE,			/* SKIP TO FIRST variable name */
+	ST_LAST_VARIABLE,			/* SKIP TO LAST variable name */
+	ST_VARIABLE					/* SKIP TO variable name */
+}			RPSkipTo;
+
+/*
+ * Row Pattern SUBSET clause item
+ */
+typedef struct RPSubsetItem
+{
+	NodeTag		type;
+	char	   *name;			/* Row Pattern SUBSET clause variable name */
+	List	   *rhsVariable;	/* Row Pattern SUBSET rhs variables (list of
+								 * char *string) */
+}			RPSubsetItem;
+
+/*
+ * RowPatternCommonSyntax - raw representation of row pattern common syntax
+ *
+ */
+typedef struct RPCommonSyntax
+{
+	NodeTag		type;
+	RPSkipTo	rpSkipTo;		/* Row Pattern AFTER MATCH SKIP type */
+	char	   *rpSkipVariable; /* Row Pattern Skip To variable name, if any */
+	bool		initial;		/* true if <row pattern initial or seek> is
+								 * initial */
+	List	   *rpPatterns;		/* PATTERN variables (list of A_Expr) */
+	List	   *rpSubsetClause; /* row pattern subset clause (list of
+								 * RPSubsetItem), if any */
+	List	   *rpDefs;			/* row pattern definitions clause (list of
+								 * ResTarget) */
+}			RPCommonSyntax;
+
 /*
  * WindowDef - raw representation of WINDOW and OVER clauses
  *
@@ -565,6 +607,9 @@ 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 */
@@ -1533,6 +1578,11 @@ 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.
  */
@@ -1562,6 +1612,23 @@ 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 f9a4afd472..df49492629 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -129,6 +129,7 @@ PG_KEYWORD("default", DEFAULT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("defaults", DEFAULTS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferrable", DEFERRABLE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferred", DEFERRED, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("define", DEFINE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("definer", DEFINER, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delete", DELETE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delimiter", DELIMITER, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -215,6 +216,7 @@ PG_KEYWORD("index", INDEX, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("indexes", INDEXES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherit", INHERIT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherits", INHERITS, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("initial", INITIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("initially", INITIALLY, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inline", INLINE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inner", INNER_P, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL)
@@ -273,6 +275,7 @@ PG_KEYWORD("match", MATCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("matched", MATCHED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("materialized", MATERIALIZED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("maxvalue", MAXVALUE, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("measures", MEASURES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge", MERGE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge_action", MERGE_ACTION, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("method", METHOD, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -338,8 +341,11 @@ PG_KEYWORD("partition", PARTITION, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("partitions", PARTITIONS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("passing", PASSING, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("password", PASSWORD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("past", PAST, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("path", PATH, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("pattern", PATTERN_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("period", PERIOD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("permute", PERMUTE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("placing", PLACING, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plan", PLAN, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plans", PLANS, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -401,6 +407,7 @@ 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)
@@ -435,6 +442,7 @@ PG_KEYWORD("strict", STRICT_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("string", STRING_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("strip", STRIP_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("subscription", SUBSCRIPTION, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("subset", SUBSET, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("substring", SUBSTRING, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("support", SUPPORT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("symmetric", SYMMETRIC, RESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h
index 5b781d87a9..66935afff8 100644
--- a/src/include/parser/parse_node.h
+++ b/src/include/parser/parse_node.h
@@ -51,6 +51,7 @@ typedef enum ParseExprKind
 	EXPR_KIND_WINDOW_FRAME_RANGE,	/* window frame clause with RANGE */
 	EXPR_KIND_WINDOW_FRAME_ROWS,	/* window frame clause with ROWS */
 	EXPR_KIND_WINDOW_FRAME_GROUPS,	/* window frame clause with GROUPS */
+	EXPR_KIND_RPR_DEFINE,		/* DEFINE */
 	EXPR_KIND_SELECT_TARGET,	/* SELECT target list item */
 	EXPR_KIND_INSERT_TARGET,	/* INSERT target list item */
 	EXPR_KIND_UPDATE_SOURCE,	/* UPDATE assignment source item */
-- 
2.25.1


----Next_Part(Sat_May_11_16_23_07_2024_789)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v18-0002-Row-pattern-recognition-patch-parse-analysis.patch"



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 416+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 416+ messages in thread