agora inbox for pgsql-hackers@postgresql.org  

help / color / mirror / Atom feed

[PATCH v19 1/8] Row pattern recognition patch for raw parser.
319+ messages / 2 participants
[nested] [flat]

* [PATCH v19 1/8] Row pattern recognition patch for raw parser.
@ 2024-05-14 23:26 Tatsuo Ishii <ishii@postgresql.org>
  0 siblings, 0 replies; 319+ messages in thread

From: Tatsuo Ishii @ 2024-05-14 23:26 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 18a0a2dc2b..010b3359d1 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		'*' '/' '%'
@@ -16316,7 +16332,8 @@ 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);
 
@@ -16324,10 +16341,12 @@ 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;
 					$$ = n;
 				}
@@ -16351,6 +16370,31 @@ opt_partition_clause: PARTITION BY expr_list		{ $$ = $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;
+					$$->location = @1;
+				}
+		;
+
 /*
  * For frame clauses, we return a WindowDef, but only some fields are used:
  * frameOptions, startOffset, and endOffset.
@@ -16510,6 +16554,143 @@ opt_window_exclusion_clause:
 			| /*EMPTY*/				{ $$ = 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.
@@ -17720,6 +17901,7 @@ unreserved_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INLINE_P
 			| INPUT_P
 			| INSENSITIVE
@@ -17748,6 +17930,7 @@ unreserved_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINUTE_P
@@ -17793,8 +17976,11 @@ unreserved_keyword:
 			| PARTITIONS
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLAN
 			| PLANS
 			| POLICY
@@ -17847,6 +18033,7 @@ unreserved_keyword:
 			| SEARCH
 			| SECOND_P
 			| SECURITY
+			| SEEK
 			| SEQUENCE
 			| SEQUENCES
 			| SERIALIZABLE
@@ -17875,6 +18062,7 @@ unreserved_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUPPORT
 			| SYSID
 			| SYSTEM_P
@@ -18069,6 +18257,7 @@ reserved_keyword:
 			| CURRENT_USER
 			| DEFAULT
 			| DEFERRABLE
+			| DEFINE
 			| DESC
 			| DISTINCT
 			| DO
@@ -18232,6 +18421,7 @@ bare_label_keyword:
 			| DEFAULTS
 			| DEFERRABLE
 			| DEFERRED
+			| DEFINE
 			| DEFINER
 			| DELETE_P
 			| DELIMITER
@@ -18309,6 +18499,7 @@ bare_label_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INITIALLY
 			| INLINE_P
 			| INNER_P
@@ -18363,6 +18554,7 @@ bare_label_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| MERGE_ACTION
 			| METHOD
@@ -18420,8 +18612,11 @@ bare_label_keyword:
 			| PARTITIONS
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLACING
 			| PLAN
 			| PLANS
@@ -18480,6 +18675,7 @@ bare_label_keyword:
 			| SCROLL
 			| SEARCH
 			| SECURITY
+			| SEEK
 			| SELECT
 			| SEQUENCE
 			| SEQUENCES
@@ -18514,6 +18710,7 @@ 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 dcfd080dd5..54427003b3 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(Wed_May_15_09_02_03_2024_008)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v19-0002-Row-pattern-recognition-patch-parse-analysis.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v2 3/6] Introduce multiple shmem segments for shared buffers
@ 2025-02-24 19:08 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-24 19:08 UTC (permalink / raw)

Add more shmem segments to split shared buffers into following chunks:
* BUFFERS_SHMEM_SEGMENT: contains buffer blocks
* BUFFER_DESCRIPTORS_SHMEM_SEGMENT: contains buffer descriptors
* BUFFER_IOCV_SHMEM_SEGMENT: contains condition variables for buffers
* CHECKPOINT_BUFFERS_SHMEM_SEGMENT: contains checkpoint buffer ids
* STRATEGY_SHMEM_SEGMENT: contains buffer strategy status

Size of the corresponding shared data directly depends on NBuffers,
meaning that if we would like to change NBuffers, they have to be
resized correspondingly. Placing each of them in a separate shmem
segment allows to achieve that.

There are some asumptions made about each of shmem segments upper size
limit. The buffer blocks have the largest, while the rest claim less
extra room for resize. Ideally those limits have to be deduced from the
maximum allowed shared memory.
---
 src/backend/port/sysv_shmem.c          | 19 ++++++-
 src/backend/storage/buffer/buf_init.c  | 79 +++++++++++++++++---------
 src/backend/storage/buffer/buf_table.c |  5 +-
 src/backend/storage/buffer/freelist.c  |  4 +-
 src/backend/storage/ipc/ipci.c         |  2 +-
 src/include/storage/bufmgr.h           |  2 +-
 src/include/storage/pg_shmem.h         | 24 +++++++-
 7 files changed, 99 insertions(+), 36 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 62f01d8218a..59aa67cb135 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -149,8 +149,13 @@ static int next_free_segment = 0;
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
  */
-Size SHMEM_EXTRA_SIZE_LIMIT[1] = {
-	0, 									/* MAIN_SHMEM_SLOT */
+Size SHMEM_EXTRA_SIZE_LIMIT[6] = {
+	0, 									/* MAIN_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 10, 	/* BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 1024 * 1, 		/* BUFFER_DESCRIPTORS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* BUFFER_IOCV_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* CHECKPOINT_BUFFERS_SHMEM_SEGMENT */
+	(Size) 1024 * 1024 * 100, 			/* STRATEGY_SHMEM_SEGMENT */
 };
 
 /* Remembers offset of the last mapping from the probe address */
@@ -179,6 +184,16 @@ MappingName(int shmem_segment)
 	{
 		case MAIN_SHMEM_SEGMENT:
 			return "main";
+		case BUFFERS_SHMEM_SEGMENT:
+			return "buffers";
+		case BUFFER_DESCRIPTORS_SHMEM_SEGMENT:
+			return "descriptors";
+		case BUFFER_IOCV_SHMEM_SEGMENT:
+			return "iocv";
+		case CHECKPOINT_BUFFERS_SHMEM_SEGMENT:
+			return "checkpoint";
+		case STRATEGY_SHMEM_SEGMENT:
+			return "strategy";
 		default:
 			return "unknown";
 	}
diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index ed1f8e03190..f5b9290a640 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -61,7 +61,10 @@ CkptSortItem *CkptBufferIds;
  * Initialize shared buffer pool
  *
  * This is called once during shared-memory initialization (either in the
- * postmaster, or in a standalone backend).
+ * postmaster, or in a standalone backend). Size of data structures initialized
+ * here depends on NBuffers, and to be able to change NBuffers without a
+ * restart we store each structure into a separate shared memory segment, which
+ * could be resized on demand.
  */
 void
 BufferManagerShmemInit(void)
@@ -73,22 +76,22 @@ BufferManagerShmemInit(void)
 
 	/* Align descriptors to a cacheline boundary. */
 	BufferDescriptors = (BufferDescPadded *)
-		ShmemInitStruct("Buffer Descriptors",
+		ShmemInitStructInSegment("Buffer Descriptors",
 						NBuffers * sizeof(BufferDescPadded),
-						&foundDescs);
+						&foundDescs, BUFFER_DESCRIPTORS_SHMEM_SEGMENT);
 
 	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
 		TYPEALIGN(PG_IO_ALIGN_SIZE,
-				  ShmemInitStruct("Buffer Blocks",
+				  ShmemInitStructInSegment("Buffer Blocks",
 								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
-								  &foundBufs));
+								  &foundBufs, BUFFERS_SHMEM_SEGMENT));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Condition Variables",
+		ShmemInitStructInSegment("Buffer IO Condition Variables",
 						NBuffers * sizeof(ConditionVariableMinimallyPadded),
-						&foundIOCV);
+						&foundIOCV, BUFFER_IOCV_SHMEM_SEGMENT);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,8 +101,9 @@ BufferManagerShmemInit(void)
 	 * painful.
 	 */
 	CkptBufferIds = (CkptSortItem *)
-		ShmemInitStruct("Checkpoint BufferIds",
-						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
+		ShmemInitStructInSegment("Checkpoint BufferIds",
+						NBuffers * sizeof(CkptSortItem), &foundBufCkpt,
+						CHECKPOINT_BUFFERS_SHMEM_SEGMENT);
 
 	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
@@ -153,33 +157,54 @@ BufferManagerShmemInit(void)
  * BufferManagerShmemSize
  *
  * compute the size of shared memory for the buffer pool including
- * data pages, buffer descriptors, hash tables, etc.
+ * data pages, buffer descriptors, hash tables, etc. based on the
+ * shared memory segment. The main segment must not allocate anything
+ * related to buffers, every other segment will receive part of the
+ * data.
  */
 Size
-BufferManagerShmemSize(void)
+BufferManagerShmemSize(int shmem_segment)
 {
 	Size		size = 0;
 
-	/* size of buffer descriptors */
-	size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
-	/* to allow aligning buffer descriptors */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == MAIN_SHMEM_SEGMENT)
+		return size;
 
-	/* size of data pages, plus alignment padding */
-	size = add_size(size, PG_IO_ALIGN_SIZE);
-	size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	if (shmem_segment == BUFFER_DESCRIPTORS_SHMEM_SEGMENT)
+	{
+		/* size of buffer descriptors */
+		size = add_size(size, mul_size(NBuffers, sizeof(BufferDescPadded)));
+		/* to allow aligning buffer descriptors */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
 
-	/* size of stuff controlled by freelist.c */
-	size = add_size(size, StrategyShmemSize());
+	if (shmem_segment == BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of data pages, plus alignment padding */
+		size = add_size(size, PG_IO_ALIGN_SIZE);
+		size = add_size(size, mul_size(NBuffers, BLCKSZ));
+	}
 
-	/* size of I/O condition variables */
-	size = add_size(size, mul_size(NBuffers,
-								   sizeof(ConditionVariableMinimallyPadded)));
-	/* to allow aligning the above */
-	size = add_size(size, PG_CACHE_LINE_SIZE);
+	if (shmem_segment == STRATEGY_SHMEM_SEGMENT)
+	{
+		/* size of stuff controlled by freelist.c */
+		size = add_size(size, StrategyShmemSize());
+	}
 
-	/* size of checkpoint sort array in bufmgr.c */
-	size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	if (shmem_segment == BUFFER_IOCV_SHMEM_SEGMENT)
+	{
+		/* size of I/O condition variables */
+		size = add_size(size, mul_size(NBuffers,
+									   sizeof(ConditionVariableMinimallyPadded)));
+		/* to allow aligning the above */
+		size = add_size(size, PG_CACHE_LINE_SIZE);
+	}
+
+	if (shmem_segment == CHECKPOINT_BUFFERS_SHMEM_SEGMENT)
+	{
+		/* size of checkpoint sort array in bufmgr.c */
+		size = add_size(size, mul_size(NBuffers, sizeof(CkptSortItem)));
+	}
 
 	return size;
 }
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index a50955d5286..ac449954dab 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -59,10 +59,11 @@ InitBufTable(int size)
 	info.entrysize = sizeof(BufferLookupEnt);
 	info.num_partitions = NUM_BUFFER_PARTITIONS;
 
-	SharedBufHash = ShmemInitHash("Shared Buffer Lookup Table",
+	SharedBufHash = ShmemInitHashInSegment("Shared Buffer Lookup Table",
 								  size, size,
 								  &info,
-								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
+								  HASH_ELEM | HASH_BLOBS | HASH_PARTITION,
+								  STRATEGY_SHMEM_SEGMENT);
 }
 
 /*
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..4919a92f2be 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -491,9 +491,9 @@ StrategyInitialize(bool init)
 	 * Get or create the shared strategy control block
 	 */
 	StrategyControl = (BufferStrategyControl *)
-		ShmemInitStruct("Buffer Strategy Status",
+		ShmemInitStructInSegment("Buffer Strategy Status",
 						sizeof(BufferStrategyControl),
-						&found);
+						&found, STRATEGY_SHMEM_SEGMENT);
 
 	if (!found)
 	{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 4f6c707c204..68778522591 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -112,7 +112,7 @@ CalculateShmemSize(int *num_semaphores, int shmem_segment)
 											 sizeof(ShmemIndexEnt)));
 	size = add_size(size, dsm_estimate_size());
 	size = add_size(size, DSMRegistryShmemSize());
-	size = add_size(size, BufferManagerShmemSize());
+	size = add_size(size, BufferManagerShmemSize(shmem_segment));
 	size = add_size(size, LockManagerShmemSize());
 	size = add_size(size, PredicateLockShmemSize());
 	size = add_size(size, ProcGlobalShmemSize());
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 7c1e4316dde..bb7fe02e243 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -297,7 +297,7 @@ extern bool EvictUnpinnedBuffer(Buffer buf);
 
 /* in buf_init.c */
 extern void BufferManagerShmemInit(void);
-extern Size BufferManagerShmemSize(void);
+extern Size BufferManagerShmemSize(int);
 
 /* in localbuf.c */
 extern void AtProcExit_LocalBuffers(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 138078c29c5..ba0192baf95 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -52,7 +52,7 @@ typedef struct ShmemSegment
 } ShmemSegment;
 
 /* Number of available segments for anonymous memory mappings */
-#define ANON_MAPPINGS 1
+#define ANON_MAPPINGS 6
 
 extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
 
@@ -105,7 +105,29 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/*
+ * To be able to dynamically resize largest parts of the data stored in shared
+ * memory, we split it into multiple shared memory mappings segments. Each
+ * segment contains only certain part of the data, which size depends on
+ * NBuffers.
+ */
+
 /* The main segment, contains everything except buffer blocks and related data. */
 #define MAIN_SHMEM_SEGMENT 0
 
+/* Buffer blocks */
+#define BUFFERS_SHMEM_SEGMENT 1
+
+/* Buffer descriptors */
+#define BUFFER_DESCRIPTORS_SHMEM_SEGMENT 2
+
+/* Condition variables for buffers */
+#define BUFFER_IOCV_SHMEM_SEGMENT 3
+
+/* Checkpoint BufferIds */
+#define CHECKPOINT_BUFFERS_SHMEM_SEGMENT 4
+
+/* Buffer strategy status */
+#define STRATEGY_SHMEM_SEGMENT 5
+
 #endif							/* PG_SHMEM_H */
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0004-Introduce-pending-flag-for-GUC-assign-hooks.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread