agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v4 1/7] Row pattern recognition patch for raw parser.
459+ messages / 2 participants
[nested] [flat]

* [PATCH v4 1/7] Row pattern recognition patch for raw parser.
@ 2023-08-09 07:56  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Tatsuo Ishii @ 2023-08-09 07:56 UTC (permalink / raw)

---
 src/backend/parser/gram.y       | 216 +++++++++++++++++++++++++++++---
 src/include/nodes/parsenodes.h  |  56 +++++++++
 src/include/parser/kwlist.h     |   8 ++
 src/include/parser/parse_node.h |   1 +
 4 files changed, 267 insertions(+), 14 deletions(-)

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 15ece871a0..62c1919538 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -251,6 +251,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	DefElem	   *defelt;
 	SortBy	   *sortby;
 	WindowDef  *windef;
+	RPCommonSyntax	*rpcom;
+	RPSubsetItem	*rpsubset;
 	JoinExpr   *jexpr;
 	IndexElem  *ielem;
 	StatsElem  *selem;
@@ -453,8 +455,12 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 				TriggerTransitions TriggerReferencing
 				vacuum_relation_list opt_vacuum_relation_list
 				drop_option_list pub_obj_list
-
-%type <node>	opt_routine_body
+				row_pattern_measure_list row_pattern_definition_list
+				opt_row_pattern_subset_clause
+				row_pattern_subset_list row_pattern_subset_rhs
+				row_pattern
+%type <rpsubset>	 row_pattern_subset_item
+%type <node>	opt_routine_body row_pattern_term
 %type <groupclause> group_clause
 %type <list>	group_by_list
 %type <node>	group_by_item empty_grouping_set rollup_clause cube_clause
@@ -551,6 +557,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %type <range>	relation_expr_opt_alias
 %type <node>	tablesample_clause opt_repeatable_clause
 %type <target>	target_el set_target insert_column_item
+				row_pattern_measure_item row_pattern_definition
 
 %type <str>		generic_option_name
 %type <node>	generic_option_arg
@@ -633,6 +640,9 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %type <list>	window_clause window_definition_list opt_partition_clause
 %type <windef>	window_definition over_clause window_specification
 				opt_frame_clause frame_extent frame_bound
+%type <rpcom>	opt_row_pattern_common_syntax opt_row_pattern_skip_to
+%type <boolean>	opt_row_pattern_initial_or_seek
+%type <list>	opt_row_pattern_measures
 %type <ival>	opt_window_exclusion_clause
 %type <str>		opt_existing_window_name
 %type <boolean> opt_if_not_exists
@@ -659,7 +669,6 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 				json_object_constructor_null_clause_opt
 				json_array_constructor_null_clause_opt
 
-
 /*
  * Non-keyword token types.  These are hard-wired into the "flex" lexer.
  * They must be listed first so that their numeric codes do not depend on
@@ -702,7 +711,7 @@ 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
 
@@ -718,7 +727,7 @@ 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
 
@@ -731,7 +740,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	LEADING LEAKPROOF LEAST LEFT LEVEL LIKE LIMIT LISTEN LOAD LOCAL
 	LOCALTIME LOCALTIMESTAMP LOCATION LOCK_P LOCKED LOGGED
 
-	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MERGE METHOD
+	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MEASURES MERGE METHOD
 	MINUTE_P MINVALUE MODE MONTH_P MOVE
 
 	NAME_P NAMES NATIONAL NATURAL NCHAR NEW NEXT NFC NFD NFKC NFKD NO NONE
@@ -743,8 +752,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	ORDER ORDINALITY OTHERS OUT_P OUTER_P
 	OVER OVERLAPS OVERLAY OVERRIDING OWNED OWNER
 
-	PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD
-	PLACING PLANS POLICY
+	PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD PAST
+	PATTERN PERMUTE PLACING PLANS POLICY
 	POSITION PRECEDING PRECISION PRESERVE PREPARE PREPARED PRIMARY
 	PRIOR PRIVILEGES PROCEDURAL PROCEDURE PROCEDURES PROGRAM PUBLICATION
 
@@ -755,12 +764,13 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
 	ROUTINE ROUTINES ROW ROWS RULE
 
-	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT
+	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SEEK SELECT
 	SEQUENCE SEQUENCES
+
 	SERIALIZABLE SERVER SESSION SESSION_USER SET SETS SETOF SHARE SHOW
 	SIMILAR SIMPLE SKIP SMALLINT SNAPSHOT SOME SQL_P STABLE STANDALONE_P
 	START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_P STRIP_P
-	SUBSCRIPTION SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
+	SUBSCRIPTION SUBSET SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
 
 	TABLE TABLES TABLESAMPLE TABLESPACE TEMP TEMPLATE TEMPORARY TEXT_P THEN
 	TIES TIME TIMESTAMP TO TRAILING TRANSACTION TRANSFORM
@@ -853,6 +863,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
  */
 %nonassoc	UNBOUNDED		/* ideally would have same precedence as IDENT */
 %nonassoc	IDENT PARTITION RANGE ROWS GROUPS PRECEDING FOLLOWING CUBE ROLLUP
+%nonassoc	MEASURES AFTER INITIAL SEEK PATTERN
 %left		Op OPERATOR		/* multi-character ops and user-defined operators */
 %left		'+' '-'
 %left		'*' '/' '%'
@@ -15832,7 +15843,8 @@ 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);
 
@@ -15840,10 +15852,12 @@ 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 = $7;
 					n->location = @1;
 					$$ = n;
 				}
@@ -15867,6 +15881,31 @@ opt_partition_clause: PARTITION BY expr_list		{ $$ = $3; }
 			| /*EMPTY*/								{ $$ = NIL; }
 		;
 
+/*
+ * ROW PATTERN 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;
+					$$->location = @1;
+				}
+		;
+
 /*
  * For frame clauses, we return a WindowDef, but only some fields are used:
  * frameOptions, startOffset, and endOffset.
@@ -16026,6 +16065,139 @@ opt_window_exclusion_clause:
 			| /*EMPTY*/				{ $$ = 0; }
 		;
 
+opt_row_pattern_common_syntax:
+opt_row_pattern_skip_to opt_row_pattern_initial_or_seek
+				PATTERN '(' row_pattern ')'
+				opt_row_pattern_subset_clause
+				DEFINE row_pattern_definition_list
+			{
+				RPCommonSyntax *n = makeNode(RPCommonSyntax);
+				n->rpSkipTo = $1->rpSkipTo;
+				n->rpSkipVariable = $1->rpSkipVariable;
+				n->initial = $2;
+				n->rpPatterns = $5;
+				n->rpSubsetClause = $7;
+				n->rpDefs = $9;
+				$$ = n;
+			}
+			| /*EMPTY*/		{ $$ = NULL; }
+	;
+
+opt_row_pattern_skip_to:
+			AFTER MATCH SKIP TO NEXT ROW
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_NEXT_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = n;
+			}
+			| AFTER MATCH SKIP PAST LAST_P ROW
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_PAST_LAST_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = n;
+				}
+/*
+			| AFTER MATCH SKIP TO FIRST_P ColId		%prec FIRST_P
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_FIRST_VARIABLE;
+					n->rpSkipVariable = $6;
+					$$ = n;
+				}
+			| AFTER MATCH SKIP TO LAST_P ColId		%prec LAST_P
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_LAST_VARIABLE;
+					n->rpSkipVariable = $6;
+					$$ = n;
+				}
+ * Shift/reduce
+			| AFTER MATCH SKIP TO ColId
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_VARIABLE;
+					n->rpSkipVariable = $5;
+					$$ = n;
+				}
+*/
+			| /*EMPTY*/
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					/* temporary set default to ST_NEXT_ROW */
+					n->rpSkipTo = ST_PAST_LAST_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = n;
+				}
+	;
+
+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*/												{ $$ = NIL; }
+		;
+
+row_pattern_subset_item: ColId '=' '(' row_pattern_subset_rhs ')'
+			{
+				RPSubsetItem *n = makeNode(RPSubsetItem);
+				n->name = $1;
+				n->rhsVariable = $4;
+				$$ = 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.
@@ -17121,6 +17293,7 @@ unreserved_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INLINE_P
 			| INPUT_P
 			| INSENSITIVE
@@ -17148,6 +17321,7 @@ unreserved_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINUTE_P
@@ -17190,6 +17364,9 @@ unreserved_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
+			| PATTERN
+			| PERMUTE
 			| PLANS
 			| POLICY
 			| PRECEDING
@@ -17240,6 +17417,7 @@ unreserved_keyword:
 			| SEARCH
 			| SECOND_P
 			| SECURITY
+			| SEEK
 			| SEQUENCE
 			| SEQUENCES
 			| SERIALIZABLE
@@ -17265,6 +17443,7 @@ unreserved_keyword:
 			| STRICT_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUPPORT
 			| SYSID
 			| SYSTEM_P
@@ -17452,6 +17631,7 @@ reserved_keyword:
 			| CURRENT_USER
 			| DEFAULT
 			| DEFERRABLE
+			| DEFINE
 			| DESC
 			| DISTINCT
 			| DO
@@ -17614,6 +17794,7 @@ bare_label_keyword:
 			| DEFAULTS
 			| DEFERRABLE
 			| DEFERRED
+			| DEFINE
 			| DEFINER
 			| DELETE_P
 			| DELIMITER
@@ -17689,6 +17870,7 @@ bare_label_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INITIALLY
 			| INLINE_P
 			| INNER_P
@@ -17738,6 +17920,7 @@ bare_label_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINVALUE
@@ -17791,6 +17974,9 @@ bare_label_keyword:
 			| PARTITION
 			| PASSING
 			| PASSWORD
+			| PAST
+			| PATTERN
+			| PERMUTE
 			| PLACING
 			| PLANS
 			| POLICY
@@ -17847,6 +18033,7 @@ bare_label_keyword:
 			| SCROLL
 			| SEARCH
 			| SECURITY
+			| SEEK
 			| SELECT
 			| SEQUENCE
 			| SEQUENCES
@@ -17878,6 +18065,7 @@ bare_label_keyword:
 			| STRICT_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUBSTRING
 			| SUPPORT
 			| SYMMETRIC
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index fe003ded50..c78bd849f9 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -547,6 +547,44 @@ typedef struct SortBy
 	int			location;		/* operator location, or -1 if none/unknown */
 } SortBy;
 
+/*
+ * AFTER MATCH row pattern skip to types in row pattern common syntax
+ */
+typedef enum RPSkipTo
+{
+	ST_NONE,					/* AFTER MATCH omitted */
+	ST_NEXT_ROW,				/* SKIP TO NEXT ROW */
+	ST_PAST_LAST_ROW,			/* SKIP TO PAST LAST ROW */
+	ST_FIRST_VARIABLE,			/* SKIP TO FIRST variable name */
+	ST_LAST_VARIABLE,			/* SKIP TO LAST variable name */
+	ST_VARIABLE					/* SKIP TO variable name */
+} RPSkipTo;
+
+/*
+ * Row Pattern SUBSET clause item
+ */
+typedef struct RPSubsetItem
+{
+	NodeTag		type;
+	char	   *name;			/* Row Pattern SUBSET clause variable name */
+	List	   *rhsVariable;	/* Row Pattern SUBSET rhs variables (list of char *string) */
+} RPSubsetItem;
+
+/*
+ * RowPatternCommonSyntax - raw representation of row pattern common syntax
+ *
+ */
+typedef struct RPCommonSyntax
+{
+	NodeTag		type;
+	RPSkipTo	rpSkipTo;		/* Row Pattern AFTER MATCH SKIP type */
+	char	   *rpSkipVariable;	/* Row Pattern Skip To variable name, if any */
+	bool		initial;		/* true if <row pattern initial or seek> is initial */
+	List	   *rpPatterns;		/* PATTERN variables (list of A_Expr) */
+	List	   *rpSubsetClause;	/* row pattern subset clause (list of RPSubsetItem), if any */
+	List	   *rpDefs;			/* row pattern definitions clause (list of ResTarget) */
+} RPCommonSyntax;
+
 /*
  * WindowDef - raw representation of WINDOW and OVER clauses
  *
@@ -562,6 +600,8 @@ 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 */
@@ -1483,6 +1523,11 @@ 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.
  */
@@ -1514,6 +1559,17 @@ 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 */
+	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 5984dcfa4b..431e0625f1 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -128,6 +128,7 @@ PG_KEYWORD("default", DEFAULT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("defaults", DEFAULTS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferrable", DEFERRABLE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferred", DEFERRED, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("define", DEFINE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("definer", DEFINER, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delete", DELETE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delimiter", DELIMITER, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -212,6 +213,7 @@ PG_KEYWORD("index", INDEX, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("indexes", INDEXES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherit", INHERIT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherits", INHERITS, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("initial", INITIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("initially", INITIALLY, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inline", INLINE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inner", INNER_P, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL)
@@ -265,6 +267,7 @@ PG_KEYWORD("match", MATCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("matched", MATCHED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("materialized", MATERIALIZED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("maxvalue", MAXVALUE, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("measures", MEASURES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge", MERGE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("method", METHOD, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("minute", MINUTE_P, UNRESERVED_KEYWORD, AS_LABEL)
@@ -326,6 +329,9 @@ PG_KEYWORD("partial", PARTIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("partition", PARTITION, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("passing", PASSING, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("password", PASSWORD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("past", PAST, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("pattern", PATTERN, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("permute", PERMUTE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("placing", PLACING, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plans", PLANS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("policy", POLICY, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -385,6 +391,7 @@ PG_KEYWORD("scroll", SCROLL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("search", SEARCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("second", SECOND_P, UNRESERVED_KEYWORD, AS_LABEL)
 PG_KEYWORD("security", SECURITY, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("seek", SEEK, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("select", SELECT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequence", SEQUENCE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequences", SEQUENCES, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -416,6 +423,7 @@ PG_KEYWORD("stored", STORED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("strict", STRICT_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("strip", STRIP_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("subscription", SUBSCRIPTION, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("subset", SUBSET, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("substring", SUBSTRING, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("support", SUPPORT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("symmetric", SYMMETRIC, RESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h
index f589112d5e..6640090910 100644
--- a/src/include/parser/parse_node.h
+++ b/src/include/parser/parse_node.h
@@ -51,6 +51,7 @@ typedef enum ParseExprKind
 	EXPR_KIND_WINDOW_FRAME_RANGE,	/* window frame clause with RANGE */
 	EXPR_KIND_WINDOW_FRAME_ROWS,	/* window frame clause with ROWS */
 	EXPR_KIND_WINDOW_FRAME_GROUPS,	/* window frame clause with GROUPS */
+	EXPR_KIND_RPR_DEFINE,		/* DEFINE */
 	EXPR_KIND_SELECT_TARGET,	/* SELECT target list item */
 	EXPR_KIND_INSERT_TARGET,	/* INSERT target list item */
 	EXPR_KIND_UPDATE_SOURCE,	/* UPDATE assignment source item */
-- 
2.25.1


----Next_Part(Wed_Aug__9_17_41_12_2023_134)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v4-0002-Row-pattern-recognition-patch-parse-analysis.patch"



^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v2] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index fb6a4914b06..1da073f0aaa 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index d3febfe58f1..075194a8af8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1844,6 +1844,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index 6d304f32fb0..d346aefe9b6 100644
--- a/meson.build
+++ b/meson.build
@@ -2694,6 +2694,7 @@ decl_checks = [
   ['strlcpy', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 563f20374ff..b41a5f9dcca 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#if HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#if HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#if HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 339268dc8ef..e7b8e023829 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -80,6 +80,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of `memset_s', and to 0 if you
    don't. */
 #undef HAVE_DECL_MEMSET_S

base-commit: 6831cd9e3b082d7b830c3196742dd49e3540c49b
-- 
2.49.0


--7u2oub7w3nl66bkx--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread

* [PATCH v1] Use open file description locks for data directory lockfile
@ 2025-12-18 17:21  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 459+ messages in thread

From: Dmitrii Dolgov @ 2025-12-18 17:21 UTC (permalink / raw)

When starting up, postmaster checks for an existing data directory lockfile. If
this file contains current process PID, it's assumed to be stale. Turns out
there is another possibility: we might be running in a PID namespace, and there
is another postgres running inside another PID namespace using the same data
directory. The result is that we don't see another process due to namespace
isolation and start concurrently with the other.

To prevent such situations, at startup use fcntl to get an exclusive open file
description lock for data directory lockfile. Since such locks are associated
with open file descriptors, meaning they're not affected by PID namespace
isolation. It's a "best effort" locking, intended to work with already existing
mechanism, not replace it.

This approach was discussed multiple times in the past, and usually was
rejected as the main work horse for the data directory lockfile due to:

* Portability issues. Open file description lock was a non-POSIX extension in
  Linux and similar flock is from BSD standard. But looks like everybody agrees
  that such locks make more sense than a typical advisory locks, and
  F_OFD_SETLK made its way into POSIX.1 2024 [1].

* Issues with NFS. The current state of things here looks like this:

  - NFSv3 doesn't implement open file description locks, they're converted to
    advisory locks instead. Advisory locks are subject to namespace isolation,
    meaning that processes in different PID namespaces will not see each other
    advisory lock, and it's still possible to run multiple postgres
    instances on the same data directory.

  - NFSv4 uses a lease system for locking, I haven't found any mention of
    conversion to advisory locks neither in the man page nor in RFC [2].

To summarize, the approach is now considered POSIX and should fix the described
problem everywhere, except NFSv3.

[1]: https://pubs.opengroup.org/onlinepubs/9799919799/functions/fcntl.html
[2]: https://www.rfc-editor.org/rfc/rfc7530
---
 configure                         |  14 ++++
 configure.ac                      |   3 +
 meson.build                       |   1 +
 src/backend/utils/init/miscinit.c | 107 +++++++++++++++++++++++++-----
 src/include/pg_config.h.in        |   4 ++
 5 files changed, 111 insertions(+), 18 deletions(-)

diff --git a/configure b/configure
index 14ad0a5006f..b176ac39799 100755
--- a/configure
+++ b/configure
@@ -16177,6 +16177,20 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
+# Linux open file descriptor locks
+ac_fn_c_check_decl "$LINENO" "F_OFD_SETLK" "ac_cv_have_decl_F_OFD_SETLK" "#include <fcntl.h>
+"
+if test "x$ac_cv_have_decl_F_OFD_SETLK" = xyes; then :
+  ac_have_decl=1
+else
+  ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_F_OFD_SETLK $ac_have_decl
+_ACEOF
+
+
 ac_fn_c_check_func "$LINENO" "explicit_bzero" "ac_cv_func_explicit_bzero"
 if test "x$ac_cv_func_explicit_bzero" = xyes; then :
   $as_echo "#define HAVE_EXPLICIT_BZERO 1" >>confdefs.h
diff --git a/configure.ac b/configure.ac
index 01b3bbc1be8..d6cf1f27771 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1838,6 +1838,9 @@ AC_CHECK_DECLS([memset_s], [], [], [#define __STDC_WANT_LIB_EXT1__ 1
 # This is probably only present on macOS, but may as well check always
 AC_CHECK_DECLS(F_FULLFSYNC, [], [], [#include <fcntl.h>])
 
+# Linux open file descriptor locks
+AC_CHECK_DECLS([F_OFD_SETLK], [], [], [#include <fcntl.h>])
+
 AC_REPLACE_FUNCS(m4_normalize([
 	explicit_bzero
 	getopt
diff --git a/meson.build b/meson.build
index d7c5193d4ce..ad9ecad829f 100644
--- a/meson.build
+++ b/meson.build
@@ -2667,6 +2667,7 @@ decl_checks = [
   ['strnlen', 'string.h'],
   ['strsep',  'string.h'],
   ['timingsafe_bcmp',  'string.h'],
+  ['F_OFD_SETLK', 'fcntl.h'],
 ]
 
 # Need to check for function declarations for these functions, because
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index fec79992c8d..78bb7df543e 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -68,6 +68,11 @@ static List *lock_files = NIL;
 
 static Latch LocalLatchData;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+/* File descriptor for data directory lock file. */
+static int DataDirLockFD;
+#endif
+
 /* ----------------------------------------------------------------
  *		ignoring system indexes support stuff
  *
@@ -1117,6 +1122,45 @@ RestoreClientConnectionInfo(char *conninfo)
  *-------------------------------------------------------------------------
  */
 
+/*
+ * Flock the data directory lockfile.
+ *
+ * Lock the data directory lockfile with an open file description lock. If the
+ * lock is already taken, it's a hard stop. It's only a best effort test, and
+ * any other errors are ignored. On succes the file descriptor is duplicated,
+ * to make sure there will be at least one open copy of it to keep the lock.
+ *
+ * filename is used only for reporting purposes.
+ */
+static void
+FlockDataDirLockFile(int fd, const char *filename)
+{
+
+#ifdef HAVE_DECL_F_OFD_SETLK
+	struct flock lock;
+
+	lock.l_type		= F_WRLCK;
+	lock.l_whence	= SEEK_SET;
+	lock.l_start	= 0;
+	lock.l_len		= 0;
+	lock.l_pid		= 0;
+
+	if (fcntl(fd, F_OFD_SETLK, &lock) == -1)
+	{
+		if (errno == EAGAIN)
+			ereport(FATAL,
+					(errcode(ERRCODE_LOCK_FILE_EXISTS),
+					 errmsg("cannot lock the lock file \"%s\"", filename),
+					 errhint("Another server is starting.")));
+		else
+			elog(WARNING, "Failed locking file \"%s\", %m", filename);
+	}
+	else
+		DataDirLockFD = dup(fd);
+#endif
+
+}
+
 /*
  * proc_exit callback to remove lockfiles.
  */
@@ -1125,6 +1169,11 @@ UnlinkLockFiles(int status, Datum arg)
 {
 	ListCell   *l;
 
+#ifdef HAVE_DECL_F_OFD_SETLK
+	/* Close the file descriptor, which keeps the open file description lock */
+	close(DataDirLockFD);
+#endif
+
 	foreach(l, lock_files)
 	{
 		char	   *curfile = (char *) lfirst(l);
@@ -1171,22 +1220,32 @@ CreateLockFile(const char *filename, bool amPostmaster,
 	const char *envvar;
 
 	/*
-	 * If the PID in the lockfile is our own PID or our parent's or
-	 * grandparent's PID, then the file must be stale (probably left over from
-	 * a previous system boot cycle).  We need to check this because of the
-	 * likelihood that a reboot will assign exactly the same PID as we had in
-	 * the previous reboot, or one that's only one or two counts larger and
-	 * hence the lockfile's PID now refers to an ancestor shell process.  We
-	 * allow pg_ctl to pass down its parent shell PID (our grandparent PID)
-	 * via the environment variable PG_GRANDPARENT_PID; this is so that
-	 * launching the postmaster via pg_ctl can be just as reliable as
-	 * launching it directly.  There is no provision for detecting
-	 * further-removed ancestor processes, but if the init script is written
-	 * carefully then all but the immediate parent shell will be root-owned
-	 * processes and so the kill test will fail with EPERM.  Note that we
-	 * cannot get a false negative this way, because an existing postmaster
-	 * would surely never launch a competing postmaster or pg_ctl process
-	 * directly.
+	 * If we find an already existing lockfile containing our own PID,
+	 * there are few options:
+	 *
+	 * - There is another process, that we don't see due to PID namespace
+	 *   isolation, which is already running in this data directory.
+	 *
+	 *   To prevent two concurrent processes working with the same data
+	 *   directory, we first try to lock the lockfile exclusively.
+	 *
+	 * - The file must be stale, probably left over from a previous system boot
+	 *   cycle. The same if the lockfile contains our parent's or grandparent's
+	 *   PID.
+	 *
+	 *   We need to check this because of the likelihood that a reboot will
+	 *   assign exactly the same PID as we had in the previous reboot, or one
+	 *   that's only one or two counts larger and hence the lockfile's PID now
+	 *   refers to an ancestor shell process.  We allow pg_ctl to pass down its
+	 *   parent shell PID (our grandparent PID) via the environment variable
+	 *   PG_GRANDPARENT_PID; this is so that launching the postmaster via
+	 *   pg_ctl can be just as reliable as launching it directly.  There is no
+	 *   provision for detecting further-removed ancestor processes, but if the
+	 *   init script is written carefully then all but the immediate parent
+	 *   shell will be root-owned processes and so the kill test will fail with
+	 *   EPERM.  Note that we cannot get a false negative this way, because an
+	 *   existing postmaster would surely never launch a competing postmaster
+	 *   or pg_ctl process directly.
 	 */
 	my_pid = getpid();
 
@@ -1222,7 +1281,11 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		 */
 		fd = open(filename, O_RDWR | O_CREAT | O_EXCL, pg_file_create_mode);
 		if (fd >= 0)
-			break;				/* Success; exit the retry loop */
+		{
+			/* Success; lock and exit the retry loop */
+			FlockDataDirLockFile(fd, filename);
+			break;
+		}
 
 		/*
 		 * Couldn't create the pid file. Probably it already exists.
@@ -1236,8 +1299,12 @@ CreateLockFile(const char *filename, bool amPostmaster,
 		/*
 		 * Read the file to get the old owner's PID.  Note race condition
 		 * here: file might have been deleted since we tried to create it.
+		 *
+		 * We're going to use the same fd for flock, and want to create a write
+		 * lock for the latter one. Since both fd and the lock have to be of
+		 * the same type, open the file for read and write.
 		 */
-		fd = open(filename, O_RDONLY, pg_file_create_mode);
+		fd = open(filename, O_RDWR, pg_file_create_mode);
 		if (fd < 0)
 		{
 			if (errno == ENOENT)
@@ -1247,6 +1314,10 @@ CreateLockFile(const char *filename, bool amPostmaster,
 					 errmsg("could not open lock file \"%s\": %m",
 							filename)));
 		}
+
+		/* Try to lock the file. We stop here, if it's already locked. */
+		FlockDataDirLockFile(fd, filename);
+
 		pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_CREATE_READ);
 		if ((len = read(fd, buffer, sizeof(buffer) - 1)) < 0)
 			ereport(FATAL,
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 92fcc5f3063..c19a50f108e 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -83,6 +83,10 @@
    don't. */
 #undef HAVE_DECL_F_FULLFSYNC
 
+/* Define to 1 if you have the declaration of `F_OFD_SETLK', and to 0 if you
+   don't. */
+#undef HAVE_DECL_F_OFD_SETLK
+
 /* Define to 1 if you have the declaration of
    `LLVMCreateGDBRegistrationListener', and to 0 if you don't. */
 #undef HAVE_DECL_LLVMCREATEGDBREGISTRATIONLISTENER

base-commit: 44f49511b7940adf3be4337d4feb2de38fe92297
-- 
2.49.0


--n6t6hie3zne7u6vd--





^ permalink  raw  reply  [nested|flat] 459+ messages in thread