agora inbox for pgsql-hackers@postgresql.org  
help / color / mirror / Atom feed
[PATCH v22 1/8] Row pattern recognition patch for raw parser.
425+ messages / 2 participants
[nested] [flat]

* [PATCH v22 1/8] Row pattern recognition patch for raw parser.
@ 2024-09-19 04:48 Tatsuo Ishii <ishii@postgresql.org>
  0 siblings, 0 replies; 425+ messages in thread

From: Tatsuo Ishii @ 2024-09-19 04:48 UTC (permalink / raw)

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

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index ab304ca989..7f111255c6 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -677,6 +677,21 @@ 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.
@@ -720,7 +735,7 @@ 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
 
@@ -736,7 +751,7 @@ 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
 
@@ -749,7 +764,7 @@ 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
@@ -761,8 +776,9 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	ORDER ORDINALITY OTHERS OUT_P OUTER_P
 	OVER OVERLAPS OVERLAY OVERRIDING OWNED OWNER
 
-	PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD PATH
-	PERIOD PLACING PLAN PLANS POLICY
+	PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD PAST
+	PATH PATTERN_P PERIOD PERMUTE PLACING PLAN PLANS POLICY
+
 	POSITION PRECEDING PRECISION PRESERVE PREPARE PREPARED PRIMARY
 	PRIOR PRIVILEGES PROCEDURAL PROCEDURE PROCEDURES PROGRAM PUBLICATION
 
@@ -773,12 +789,13 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
 	ROUTINE ROUTINES ROW ROWS RULE
 
-	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT
+	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SEEK SELECT
 	SEQUENCE SEQUENCES
+
 	SERIALIZABLE SERVER SESSION SESSION_USER SET SETS SETOF SHARE SHOW
 	SIMILAR SIMPLE SKIP SMALLINT SNAPSHOT SOME SOURCE SQL_P STABLE STANDALONE_P
 	START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_P STRING_P STRIP_P
-	SUBSCRIPTION SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
+	SUBSCRIPTION SUBSET SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
 
 	TABLE TABLES TABLESAMPLE TABLESPACE TARGET TEMP TEMPLATE TEMPORARY TEXT_P THEN
 	TIES TIME TIMESTAMP TO TRAILING TRANSACTION TRANSFORM
@@ -887,6 +904,7 @@ 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		'*' '/' '%'
@@ -16252,7 +16270,8 @@ 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);
 
@@ -16260,10 +16279,12 @@ 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;
 					$$ = n;
 				}
@@ -16287,6 +16308,31 @@ opt_partition_clause: PARTITION BY expr_list		{ $$ = $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;
+					$$->location = @1;
+				}
+		;
+
 /*
  * For frame clauses, we return a WindowDef, but only some fields are used:
  * frameOptions, startOffset, and endOffset.
@@ -16446,6 +16492,143 @@ opt_window_exclusion_clause:
 			| /*EMPTY*/				{ $$ = 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.
@@ -17656,6 +17839,7 @@ unreserved_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INLINE_P
 			| INPUT_P
 			| INSENSITIVE
@@ -17684,6 +17868,7 @@ unreserved_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINUTE_P
@@ -17728,8 +17913,11 @@ unreserved_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLAN
 			| PLANS
 			| POLICY
@@ -17781,6 +17969,7 @@ unreserved_keyword:
 			| SEARCH
 			| SECOND_P
 			| SECURITY
+			| SEEK
 			| SEQUENCE
 			| SEQUENCES
 			| SERIALIZABLE
@@ -17808,6 +17997,7 @@ unreserved_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUPPORT
 			| SYSID
 			| SYSTEM_P
@@ -18002,6 +18192,7 @@ reserved_keyword:
 			| CURRENT_USER
 			| DEFAULT
 			| DEFERRABLE
+			| DEFINE
 			| DESC
 			| DISTINCT
 			| DO
@@ -18165,6 +18356,7 @@ bare_label_keyword:
 			| DEFAULTS
 			| DEFERRABLE
 			| DEFERRED
+			| DEFINE
 			| DEFINER
 			| DELETE_P
 			| DELIMITER
@@ -18242,6 +18434,7 @@ bare_label_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INITIALLY
 			| INLINE_P
 			| INNER_P
@@ -18296,6 +18489,7 @@ bare_label_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| MERGE_ACTION
 			| METHOD
@@ -18352,8 +18546,11 @@ bare_label_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
 			| PERIOD
+			| PERMUTE
 			| PLACING
 			| PLAN
 			| PLANS
@@ -18411,6 +18608,7 @@ bare_label_keyword:
 			| SCROLL
 			| SEARCH
 			| SECURITY
+			| SEEK
 			| SELECT
 			| SEQUENCE
 			| SEQUENCES
@@ -18444,6 +18642,7 @@ 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 e62ce1b753..8e4f27a00f 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -552,6 +552,48 @@ typedef struct SortBy
 	ParseLoc	location;		/* operator location, or -1 if none/unknown */
 } SortBy;
 
+/*
+ * AFTER MATCH row pattern skip to types in row pattern common syntax
+ */
+typedef enum RPSkipTo
+{
+	ST_NONE,					/* AFTER MATCH omitted */
+	ST_NEXT_ROW,				/* SKIP TO NEXT ROW */
+	ST_PAST_LAST_ROW,			/* SKIP TO PAST LAST ROW */
+	ST_FIRST_VARIABLE,			/* SKIP TO FIRST variable name */
+	ST_LAST_VARIABLE,			/* SKIP TO LAST variable name */
+	ST_VARIABLE					/* SKIP TO variable name */
+}			RPSkipTo;
+
+/*
+ * Row Pattern SUBSET clause item
+ */
+typedef struct RPSubsetItem
+{
+	NodeTag		type;
+	char	   *name;			/* Row Pattern SUBSET clause variable name */
+	List	   *rhsVariable;	/* Row Pattern SUBSET rhs variables (list of
+								 * char *string) */
+}			RPSubsetItem;
+
+/*
+ * RowPatternCommonSyntax - raw representation of row pattern common syntax
+ *
+ */
+typedef struct RPCommonSyntax
+{
+	NodeTag		type;
+	RPSkipTo	rpSkipTo;		/* Row Pattern AFTER MATCH SKIP type */
+	char	   *rpSkipVariable; /* Row Pattern Skip To variable name, if any */
+	bool		initial;		/* true if <row pattern initial or seek> is
+								 * initial */
+	List	   *rpPatterns;		/* PATTERN variables (list of A_Expr) */
+	List	   *rpSubsetClause; /* row pattern subset clause (list of
+								 * RPSubsetItem), if any */
+	List	   *rpDefs;			/* row pattern definitions clause (list of
+								 * ResTarget) */
+}			RPCommonSyntax;
+
 /*
  * WindowDef - raw representation of WINDOW and OVER clauses
  *
@@ -567,6 +609,9 @@ typedef struct WindowDef
 	char	   *refname;		/* referenced window name, if any */
 	List	   *partitionClause;	/* PARTITION BY expression list */
 	List	   *orderClause;	/* ORDER BY (list of SortBy) */
+	List	   *rowPatternMeasures; /* row pattern measures (list of
+									 * ResTarget) */
+	RPCommonSyntax *rpCommonSyntax; /* row pattern common syntax */
 	int			frameOptions;	/* frame_clause options, see below */
 	Node	   *startOffset;	/* expression for starting bound, if any */
 	Node	   *endOffset;		/* expression for ending bound, if any */
@@ -1529,6 +1574,11 @@ 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.
  */
@@ -1558,6 +1608,23 @@ typedef struct WindowClause
 	Index		winref;			/* ID referenced by window functions */
 	/* did we copy orderClause from refname? */
 	bool		copiedOrder pg_node_attr(query_jumble_ignore);
+	/* Row Pattern AFTER MACH SKIP clause */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */
+	char	   *rpSkipVariable; /* Row Pattern Skip To variable */
+	bool		initial;		/* true if <row pattern initial or seek> is
+								 * initial */
+	/* Row Pattern DEFINE clause (list of TargetEntry) */
+	List	   *defineClause;
+	/* Row Pattern DEFINE variable initial names (list of String) */
+	List	   *defineInitial;
+	/* Row Pattern PATTERN variable name (list of String) */
+	List	   *patternVariable;
+
+	/*
+	 * Row Pattern PATTERN regular expression quantifier ('+' or ''. list of
+	 * String)
+	 */
+	List	   *patternRegexp;
 } WindowClause;
 
 /*
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index 899d64ad55..f52d797615 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -129,6 +129,7 @@ PG_KEYWORD("default", DEFAULT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("defaults", DEFAULTS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferrable", DEFERRABLE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferred", DEFERRED, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("define", DEFINE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("definer", DEFINER, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delete", DELETE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delimiter", DELIMITER, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -215,6 +216,7 @@ PG_KEYWORD("index", INDEX, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("indexes", INDEXES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherit", INHERIT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherits", INHERITS, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("initial", INITIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("initially", INITIALLY, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inline", INLINE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inner", INNER_P, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL)
@@ -273,6 +275,7 @@ PG_KEYWORD("match", MATCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("matched", MATCHED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("materialized", MATERIALIZED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("maxvalue", MAXVALUE, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("measures", MEASURES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge", MERGE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge_action", MERGE_ACTION, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("method", METHOD, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -337,8 +340,11 @@ PG_KEYWORD("partial", PARTIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("partition", PARTITION, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("passing", PASSING, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("password", PASSWORD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("past", PAST, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("path", PATH, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("pattern", PATTERN_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("period", PERIOD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("permute", PERMUTE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("placing", PLACING, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plan", PLAN, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plans", PLANS, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -399,6 +405,7 @@ PG_KEYWORD("scroll", SCROLL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("search", SEARCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("second", SECOND_P, UNRESERVED_KEYWORD, AS_LABEL)
 PG_KEYWORD("security", SECURITY, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("seek", SEEK, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("select", SELECT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequence", SEQUENCE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequences", SEQUENCES, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -432,6 +439,7 @@ PG_KEYWORD("strict", STRICT_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("string", STRING_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("strip", STRIP_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("subscription", SUBSCRIPTION, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("subset", SUBSET, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("substring", SUBSTRING, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("support", SUPPORT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("symmetric", SYMMETRIC, RESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h
index 543df56814..2d270f443b 100644
--- a/src/include/parser/parse_node.h
+++ b/src/include/parser/parse_node.h
@@ -51,6 +51,7 @@ typedef enum ParseExprKind
 	EXPR_KIND_WINDOW_FRAME_RANGE,	/* window frame clause with RANGE */
 	EXPR_KIND_WINDOW_FRAME_ROWS,	/* window frame clause with ROWS */
 	EXPR_KIND_WINDOW_FRAME_GROUPS,	/* window frame clause with GROUPS */
+	EXPR_KIND_RPR_DEFINE,		/* DEFINE */
 	EXPR_KIND_SELECT_TARGET,	/* SELECT target list item */
 	EXPR_KIND_INSERT_TARGET,	/* INSERT target list item */
 	EXPR_KIND_UPDATE_SOURCE,	/* UPDATE assignment source item */
-- 
2.25.1


----Next_Part(Thu_Sep_19_13_59_47_2024_608)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v22-0002-Row-pattern-recognition-patch-parse-analysis.patch"



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v1 4/5] Allow to resize shared memory without restart
@ 2024-10-16 18:24 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2024-10-16 18:24 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Size for every shared memory slot is recalculated based on the new
NBuffers, and extended using mremap. After allocating new space, new
shared structures (buffer blocks, descriptors, etc) are allocated as
needed. Here is how it looks like after raising shared_buffers from 128
MB to 512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v2 5/6] Allow to resize shared memory without restart
@ 2025-02-20 20:12 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-02-20 20:12 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a global
Barrier to coordinate backends that simultaneously change
shared_buffers, and pieces in shared memory to coordinate backends that
are too late to the party for some reason.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier. Afterwards it does shared memory
  resize itself.

* All the backends, that participate in ProcSignal mechanism,
  recalculate shared memory size based on the new NBuffers and extend it
  using mremap.

* When finished, a backend waits on a global ShmemControl barrier,
  untill all backends will be finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all backends are using new value, one backend will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f5a2bd04000-7f5a32e52000  /dev/zero (deleted)
    7f5a39252000-7f5a4030e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d7ba000  /dev/zero (deleted)
    7f5a53bba000-7f5a5ad26000  /dev/zero (deleted)
    7f5a9ad26000-7f5aa9d94000  /dev/zero (deleted)
    ^ buffers mapping, ~240 MB
    7f5d29d94000-7f5d30e00000  /dev/zero (deleted)

    -- 512 MB
    7f5a2bd04000-7f5a33274000  /dev/zero (deleted)
    7f5a39252000-7f5a4057e000  /dev/zero (deleted)
    7f5a4670e000-7f5a4d9fa000  /dev/zero (deleted)
    7f5a53bba000-7f5a5b1a6000  /dev/zero (deleted)
    7f5a9ad26000-7f5ac1f14000  /dev/zero (deleted)
    ^ buffers mapping, ~625 MB
    7f5d29d94000-7f5d30f80000  /dev/zero (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v4 6/8] Allow to resize shared memory without restart
@ 2025-04-06 14:47 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-04-06 14:47 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers and extend it using mremap. One elected process signals the
  postmaster to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f90cde00000-7f90d4fa6000  /dev/zero (deleted)
    7f90d4fa6000-7f914de00000
    7f914de00000-7f915cfa8000  /dev/zero (deleted)
    ^ buffers mapping, ~241 MB
    7f915cfa8000-7f944de00000
    7f944de00000-7f94550a8000  /dev/zero (deleted)
    7f94550a8000-7f94cde00000
    7f94cde00000-7f94d4fe8000  /dev/zero (deleted)
    7f94d4fe8000-7f954de00000
    7f954de00000-7f9554ff6000  /dev/zero (deleted)
    7f9554ff6000-7f958de00000
    7f958de00000-7f959508a000  /dev/zero (deleted)
    7f959508a000-7f95cde00000

    -- 512 MB
    7f90cde00000-7f90d5126000  /dev/zero (deleted)
    7f90d5126000-7f914de00000
    7f914de00000-7f9175128000  /dev/zero (deleted)
    ^ buffers mapping, ~627 MB
    7f9175128000-7f944de00000
    7f944de00000-7f9455528000  /dev/zero (deleted)
    7f9455528000-7f94cde00000
    7f94cde00000-7f94d5228000  /dev/zero (deleted)
    7f94d5228000-7f954de00000
    7f954de00000-7f9555266000  /dev/zero (deleted)
    7f9555266000-7f958de00000
    7f958de00000-7f95954aa000  /dev/zero (deleted)
    7f95954aa000-7f95cde00000

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread

* [PATCH v5 07/10] Allow to resize shared memory without restart
@ 2025-06-17 12:16 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 425+ messages in thread

From: Dmitrii Dolgov @ 2025-06-17 12:16 UTC (permalink / raw)

Add assing hook for shared_buffers to resize shared memory using space,
introduced in the previous commits without requiring PostgreSQL restart.
Essentially the implementation is based on two mechanisms: a
ProcSignalBarrier is used to make sure all processes are starting the
resize procedure simultaneously, and a global Barrier is used to
coordinate after that and make sure all finished processes are waiting
for others that are in progress.

The resize process looks like this:

* The GUC assign hook sets a flag to let the Postmaster know that resize
  was requested.

* Postmaster verifies the flag in the event loop, and starts the resize
  by emitting a ProcSignal barrier.

* All processes, that participate in ProcSignal mechanism, begin to
  process ProcSignal barrier. First a process waits until all processes
  have confirmed they received the message and can start simultaneously.

* Every process recalculates shared memory size based on the new
  NBuffers, adjusts its size using ftruncate and adjust reservation
  permissions with mprotect. One elected process signals the postmaster
  to do the same.

* When finished, every process waits on a global ShmemControl barrier,
  untill all others are finished as well. This way we ensure three
  stages with clear boundaries: before the resize, when all processes
  use old NBuffers; during the resize, when processes have mix of old
  and new NBuffers, and wait until it's done; after the resize, when all
  processes use new NBuffers.

* After all processes are using new value, one of them will initialize
  new shared structures (buffer blocks, descriptors, etc) as needed and
  broadcast new value of NBuffers via ShmemControl in shared memory.
  Other backends are waiting for this operation to finish as well. Then
  the barrier is lifted and everything goes as usual.

Since resizing takes time, we need to take into account that during that time:

- New backends can be spawned. They will check status of the barrier
  early during the bootstrap, and wait until everything is over to work
  with the new NBuffers value.

- Old backends can exit before attempting to resize. Synchronization
  used between backends relies on ProcSignalBarrier and waits for all
  participants received the message at the beginning to gather all
  existing backends.

- Some backends might be blocked and not responsing either before or
  after receiving the message. In the first case such backend still
  have ProcSignalSlot and should be waited for, in the second case
  shared barrier will make sure we still waiting for those backends. In
  any case there is an unbounded wait.

- Backends might join barrier in disjoint groups with some time in
  between. That means that relying only on the shared dynamic barrier is
  not enough -- it will only synchronize resize procedure withing those
  groups. That's why we wait first for all participants of ProcSignal
  mechanism who received the message.

Here is how it looks like after raising shared_buffers from 128 MB to
512 MB and calling pg_reload_conf():

    -- 128 MB
    7f87909fc000-7f8798248000 rw-s /memfd:strategy (deleted)
    7f8798248000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a4e84000 rw-s /memfd:checkpoint (deleted)
    7f87a4e84000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1b42000 rw-s /memfd:iocv (deleted)
    7f87b1b42000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cb59c000 rw-s /memfd:descriptors (deleted)
    7f87cb59c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f87ece38000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~247 MB
    7f87ece38000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~2210 MB
    7f8877066000-7f887e7d0000 rw-s /memfd:main (deleted)
    7f887e7d0000-7f8890a00000 ---s /memfd:main (deleted)

    -- 512 MB
    7f87909fc000-7f879866a000 rw-s /memfd:strategy (deleted)
    7f879866a000-7f879d6ca000 ---s /memfd:strategy (deleted)
    7f879d6ca000-7f87a50f4000 rw-s /memfd:checkpoint (deleted)
    7f87a50f4000-7f87aa398000 ---s /memfd:checkpoint (deleted)
    7f87aa398000-7f87b1d82000 rw-s /memfd:iocv (deleted)
    7f87b1d82000-7f87c3d32000 ---s /memfd:iocv (deleted)
    7f87c3d32000-7f87cba1c000 rw-s /memfd:descriptors (deleted)
    7f87cba1c000-7f87dd6cc000 ---s /memfd:descriptors (deleted)
    7f87dd6cc000-7f8804fb8000 rw-s /memfd:buffers (deleted)
    ^ buffers content, ~632 MB
    7f8804fb8000-7f8877066000 ---s /memfd:buffers (deleted)
    ^ reserved space, ~1824 MB
    7f8877066000-7f887e950000 rw-s /memfd:main (deleted)
    7f887e950000-7f8890a00000 ---s /memfd:main (deleted)

The implementation supports only increasing of shared_buffers. For
decreasing the value a similar procedure is needed. But the buffer
blocks with data have to be drained first, so that the actual data set
fits into the new smaller space.



^ permalink  raw  reply  [nested|flat] 425+ messages in thread


end of thread, other threads:[~2025-06-17 12:16 UTC | newest]

Thread overview: 425+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2024-09-19 04:48 [PATCH v22 1/8] Row pattern recognition patch for raw parser. Tatsuo Ishii <ishii@postgresql.org>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-16 18:24 [PATCH v1 4/5] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-20 20:12 [PATCH v2 5/6] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-04-06 14:47 [PATCH v4 6/8] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>
2025-06-17 12:16 [PATCH v5 07/10] Allow to resize shared memory without restart Dmitrii Dolgov <9erthalion6@gmail.com>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox