[PATCH v3 4/7] Row pattern recognition patch (executor).

agora inbox for pgsql-hackers@postgresql.org  
help / color / mirror / Atom feed

[PATCH v3 4/7] Row pattern recognition patch (executor).
319+ messages / 2 participants
[nested] [flat]

* [PATCH v3 4/7] Row pattern recognition patch (executor).
@ 2023-07-26 10:49 Tatsuo Ishii <ishii@postgresql.org>
  0 siblings, 0 replies; 319+ messages in thread

From: Tatsuo Ishii @ 2023-07-26 10:49 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 701 ++++++++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  |  38 +-
 src/include/catalog/pg_proc.dat      |   6 +
 src/include/nodes/execnodes.h        |  18 +
 src/include/windowapi.h              |   8 +
 5 files changed, 758 insertions(+), 13 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..0586bf57d6 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -36,6 +36,7 @@
 #include "access/htup_details.h"
 #include "catalog/objectaccess.h"
 #include "catalog/pg_aggregate.h"
+#include "catalog/pg_collation_d.h"
 #include "catalog/pg_proc.h"
 #include "executor/executor.h"
 #include "executor/nodeWindowAgg.h"
@@ -48,6 +49,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +161,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -182,8 +192,9 @@ static void begin_partition(WindowAggState *winstate);
 static void spool_tuples(WindowAggState *winstate, int64 pos);
 static void release_partition(WindowAggState *winstate);
 
-static int	row_is_in_frame(WindowAggState *winstate, int64 pos,
+static int  row_is_in_frame(WindowAggState *winstate, int64 pos,
 							TupleTableSlot *slot);
+
 static void update_frameheadpos(WindowAggState *winstate);
 static void update_frametailpos(WindowAggState *winstate);
 static void update_grouptailpos(WindowAggState *winstate);
@@ -195,9 +206,19 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
+static int row_is_in_reduced_frame(WindowObject winobj, int64 pos);
+
+static int64 evaluate_pattern(WindowObject winobj, int64 current_pos, 
+							  char *vname, StringInfo encoded_str, bool *result);
+
+static bool get_slots(WindowObject winobj, int64 current_pos);
+
+static int search_str_set(char *pattern, StringInfo *str_set, int set_size);
+static void search_str_set_recurse(char *pattern, StringInfo *str_set, int set_size, int set_index,
+								   char *encoded_str, int *resultlen);
 
 /*
  * initialize_windowaggregate
@@ -673,6 +694,9 @@ eval_windowaggregates(WindowAggState *winstate)
 	WindowObject agg_winobj;
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot;
+	bool		reduced_frame_set;
+	bool		check_reduced_frame;
+	int			num_rows_in_reduced_frame;
 
 	numaggs = winstate->numaggs;
 	if (numaggs == 0)
@@ -790,6 +814,7 @@ eval_windowaggregates(WindowAggState *winstate)
 			(winstate->frameOptions & FRAMEOPTION_EXCLUSION) ||
 			winstate->aggregatedupto <= winstate->frameheadpos)
 		{
+			elog(DEBUG1, "peraggstate->restart  is set");
 			peraggstate->restart = true;
 			numaggs_restart++;
 		}
@@ -861,8 +886,10 @@ eval_windowaggregates(WindowAggState *winstate)
 	 * If we created a mark pointer for aggregates, keep it pushed up to frame
 	 * head, so that tuplestore can discard unnecessary rows.
 	 */
+#ifdef NOT_USED
 	if (agg_winobj->markptr >= 0)
 		WinSetMarkPosition(agg_winobj, winstate->frameheadpos);
+#endif
 
 	/*
 	 * Now restart the aggregates that require it.
@@ -919,6 +946,10 @@ eval_windowaggregates(WindowAggState *winstate)
 		ExecClearTuple(agg_row_slot);
 	}
 
+	reduced_frame_set = false;
+	check_reduced_frame = false;
+	num_rows_in_reduced_frame = 0;
+
 	/*
 	 * Advance until we reach a row not in frame (or end of partition).
 	 *
@@ -930,12 +961,18 @@ eval_windowaggregates(WindowAggState *winstate)
 	{
 		int			ret;
 
+		elog(DEBUG1, "===== loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
 		/* Fetch next row if we didn't already */
 		if (TupIsNull(agg_row_slot))
 		{
 			if (!window_gettupleslot(agg_winobj, winstate->aggregatedupto,
 									 agg_row_slot))
+			{
+				if (check_reduced_frame)
+					winstate->aggregatedupto--;
 				break;			/* must be end of partition */
+			}
 		}
 
 		/*
@@ -944,10 +981,47 @@ eval_windowaggregates(WindowAggState *winstate)
 		 */
 		ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot);
 		if (ret < 0)
+		{
+			if (winstate->patternVariableList != NIL && check_reduced_frame)
+				winstate->aggregatedupto--;
 			break;
+		}
 		if (ret == 0)
 			goto next_tuple;
 
+		if (winstate->patternVariableList != NIL)
+		{
+			if (!reduced_frame_set)
+			{
+				num_rows_in_reduced_frame = row_is_in_reduced_frame(winstate->agg_winobj, winstate->aggregatedupto);
+				reduced_frame_set = true;
+				elog(DEBUG1, "set num_rows_in_reduced_frame: %d pos: " INT64_FORMAT,
+					 num_rows_in_reduced_frame, winstate->aggregatedupto);
+
+				if (num_rows_in_reduced_frame <= 0)
+					break;
+
+				else if (num_rows_in_reduced_frame > 0)
+					check_reduced_frame = true;
+			}
+
+			if (check_reduced_frame)
+			{
+				elog(DEBUG1, "decrease num_rows_in_reduced_frame: %d pos: " INT64_FORMAT,
+					 num_rows_in_reduced_frame, winstate->aggregatedupto);
+				num_rows_in_reduced_frame--;
+				if (num_rows_in_reduced_frame < 0)
+				{
+					/*
+					 * No more rows remain in the reduced frame. Finish
+					 * accumulating row into the aggregates.
+					 */
+					winstate->aggregatedupto--;
+					break;
+				}
+			}
+		}
+
 		/* Set tuple context for evaluation of aggregate arguments */
 		winstate->tmpcontext->ecxt_outertuple = agg_row_slot;
 
@@ -976,6 +1050,8 @@ next_tuple:
 		ExecClearTuple(agg_row_slot);
 	}
 
+	elog(DEBUG1, "===== break loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
 	/* The frame's end is not supposed to move backwards, ever */
 	Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto);
 
@@ -2053,6 +2129,8 @@ ExecWindowAgg(PlanState *pstate)
 
 	CHECK_FOR_INTERRUPTS();
 
+	elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT , winstate->currentpos);
+
 	if (winstate->status == WINDOWAGG_DONE)
 		return NULL;
 
@@ -2388,6 +2466,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2567,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2761,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (nargs != 1)
+				continue;
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				continue;
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2831,77 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			elog(DEBUG1, "walker: varattno: %d varattnosyn: %d",attno, attnosyn);
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2919,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2970,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3312,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3100,7 +3332,7 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 		return false;
 
 	if (pos < winobj->markpos)
-		elog(ERROR, "cannot fetch row before WindowObject's mark position");
+		elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT,  pos, winobj->markpos );
 
 	oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory);
 
@@ -3420,14 +3652,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+	int			num_reduced_frame;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3494,6 +3766,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 						 winstate->frameOptions);
 					break;
 			}
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				if (relpos >= num_reduced_frame)
+					goto out_of_frame;
 			break;
 		case WINDOW_SEEK_TAIL:
 			/* rejecting relpos > 0 is easy and simplifies code below */
@@ -3565,6 +3843,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 					mark_pos = 0;	/* keep compiler quiet */
 					break;
 			}
+
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos + relpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				abs_pos = winstate->frameheadpos + relpos + num_reduced_frame - 1;
 			break;
 		default:
 			elog(ERROR, "unrecognized window seek type: %d", seektype);
@@ -3583,15 +3867,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3904,400 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
+
+/*
+ * row_is_in_reduced_frame
+ * Determine whether a row is in the current row's reduced window frame according
+ * to row pattern matching
+ *
+ * The row must has been already determined that it is in a full window frame
+ * and fetched it into slot.
+ *
+ * Returns:
+ * = 0, RPR is not defined.
+ * >0, if the row is the first in the reduced frame. Return the number of rows in the reduced frame.
+ * -1, if the row is unmatched row
+ * -2, if the row is in the reduced frame but needed to be skipped because of
+ * AFTER MATCH SKIP PAST LAST ROW
+ */
+static
+int row_is_in_reduced_frame(WindowObject winobj, int64 pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	ListCell	*lc1, *lc2;
+	bool		expression_result;
+	int			num_matched_rows;
+	int64		original_pos;
+	bool		anymatch;
+	StringInfo	encoded_str;
+	StringInfo	pattern_str = makeStringInfo();
+
+	/*
+	 * Array of pattern variables evaluted to true.
+	 * Each character corresponds to pattern variable.
+	 * Example:
+	 * str_set[0] = "AB";
+	 * str_set[1] = "AC";
+	 * In this case at row 0 A and B are true, and A and C are true in row 1.
+	 */
+	#define ENCODED_STR_ARRAY_ALLOC_SIZE	128
+	StringInfo	*str_set = NULL;
+	int		str_set_index;
+	int		str_set_size;
+
+	if (winstate->patternVariableList == NIL)
+	{
+		/*
+		 * RPR is not defined. Assume that we are always in the the reduced
+		 * window frame.
+		 */
+		return 0;
+	}
+
+	/* save original pos */
+	original_pos = pos;
+
+	/*
+	 * Check whether the row speicied by pos is in the reduced frame. The
+	 * second and subsequent rows need to be recognized as "unmatched" rows if
+	 * AFTER MATCH SKIP PAST LAST ROW is defined.
+	 */
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW &&
+		pos > winstate->headpos_in_reduced_frame &&
+		pos < (winstate->headpos_in_reduced_frame + winstate->num_rows_in_reduced_frame))
+		return -2;
+		
+	/*
+	 * Loop over until none of pattern matches or encounters end of frame.
+	 */
+	for (;;)
+	{
+		int64	result_pos = -1;
+
+		/*
+		 * Loop over each PATTERN variable.
+		 */
+		anymatch = false;
+		encoded_str = makeStringInfo();
+
+		forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+		{
+			char	*vname = strVal(lfirst(lc1));
+			char	*quantifier = strVal(lfirst(lc2));
+
+			elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", pos, vname, quantifier);
+
+			expression_result = false;
+
+			/* evaluate row pattern against current row */
+			result_pos = evaluate_pattern(winobj, pos, vname, encoded_str, &expression_result);
+			if (expression_result)
+			{
+				elog(DEBUG1, "expression result is true");
+				anymatch = true;
+			}
+
+			/*
+			 * If out of frame, we are done.
+			 */
+			 if (result_pos < 0)
+				 break;
+		}
+
+		if (!anymatch)
+		{
+			/* none of patterns matched. */
+			break;
+		}
+
+		/* build encoded string array */
+		if (str_set == NULL)
+		{
+			str_set_index = 0;
+			str_set_size = ENCODED_STR_ARRAY_ALLOC_SIZE * sizeof(StringInfo);
+			str_set = palloc(str_set_size);
+		}
+
+		str_set[str_set_index++] = encoded_str;
+
+		elog(DEBUG1, "pos: " INT64_FORMAT " str_set_index: %d encoded_str: %s", pos, str_set_index, encoded_str->data);
+
+		if (str_set_index >= str_set_size)
+		{
+			str_set_size *= 2;
+			str_set = repalloc(str_set, str_set_size);
+		}
+
+		/* move to next row */
+		pos++;
+
+		if (result_pos < 0)
+		{
+			/* out of frame */
+			break;
+		}
+	}
+
+	if (str_set == NULL)
+	{
+		/* no matches found in the first row */
+		return -1;
+	}
+
+	elog(DEBUG1, "pos: " INT64_FORMAT " encoded_str: %s", pos, encoded_str->data);
+
+	/* build regular expression */
+	pattern_str = makeStringInfo();
+	appendStringInfoChar(pattern_str, '^');
+	forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc1));
+		char	*quantifier = strVal(lfirst(lc2));
+
+		appendStringInfoChar(pattern_str, vname[0]);
+		if (quantifier[0])
+			appendStringInfoChar(pattern_str, quantifier[0]);
+		elog(DEBUG1, "vname: %s quantifier: %s", vname, quantifier);
+	}
+
+	elog(DEBUG1, "pos: " INT64_FORMAT " pattern: %s", pos, pattern_str->data);
+
+	/* look for matching pattern variable sequence */
+	num_matched_rows = search_str_set(pattern_str->data, str_set, str_set_index);
+	if (num_matched_rows <= 0)
+		return -1;
+
+	/*
+	 * We are at the first row in the reduced frame.  Save the number of
+	 * matched rows as the number of rows in the reduced frame.
+	 */
+	winstate->headpos_in_reduced_frame = original_pos;
+	winstate->num_rows_in_reduced_frame = num_matched_rows;
+
+	return num_matched_rows;
+}
+
+/*
+ * search set of encode_str.
+ * set_size: size of set_str array.
+ */
+static
+int search_str_set(char *pattern, StringInfo *str_set, int set_size)
+{
+	char		*encoded_str = palloc0(set_size+1);
+	int			resultlen = 0;
+
+	search_str_set_recurse(pattern, str_set, set_size, 0, encoded_str, &resultlen);
+	elog(DEBUG1, "search_str_set returns %d", resultlen);
+	return resultlen;
+}
+
+static
+void search_str_set_recurse(char *pattern, StringInfo *str_set, int set_size, int set_index, char *encoded_str, int *resultlen)
+{
+	char	*p;
+
+	if (set_index >= set_size)
+	{
+		Datum	d;
+		text	*res;
+		char	*substr;
+
+		/*
+		 * We first perform pattern matching using regexp_instr, then call
+		 * textregexsubstr to get matched substring to know how log the
+		 * matched string is. That is the number of rows in the reduced window
+		 * frame.  The reason why we can't call textregexsubstr is, it error
+		 * out if pattern is not match.
+		 */
+		if (DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+												  PointerGetDatum(cstring_to_text(encoded_str)),
+												  PointerGetDatum(cstring_to_text(pattern)))) > 0)
+		{
+			d = DirectFunctionCall2Coll(textregexsubstr,
+										DEFAULT_COLLATION_OID,
+										PointerGetDatum(cstring_to_text(encoded_str)),
+										PointerGetDatum(cstring_to_text(pattern)));
+			if (d != 0)
+			{
+				int		len;
+
+				res = DatumGetTextPP(d);
+				substr = text_to_cstring(res);
+				len = strlen(substr);
+				if (len > *resultlen)
+					/* remember the longest match */
+					*resultlen = len;
+			}
+		}
+		return;
+	}
+
+	p = str_set[set_index]->data;
+	while (*p)
+	{
+		encoded_str[set_index] = *p;
+		p++;
+		search_str_set_recurse(pattern, str_set, set_size, set_index + 1, encoded_str, resultlen);
+	}
+}
+
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match absolute row position
+ * other wise out of frame.
+ */
+static
+int64 evaluate_pattern(WindowObject winobj, int64 current_pos, 
+						char *vname, StringInfo encoded_str, bool *result)
+{
+	WindowAggState	*winstate = winobj->winstate;
+	ExprContext		*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell		*lc1, *lc2;
+	ExprState		*pat;
+	Datum			eval_result;
+	bool			out_of_frame = false;
+	bool			isnull;
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		/* get current, previous and next tuples */
+		if (!get_slots(winobj, current_pos))
+		{
+			out_of_frame = true;
+		}
+		else
+		{
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, vname, current_pos);
+				*result = false;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, vname, current_pos);
+					*result = false;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, vname, current_pos);
+					appendStringInfoChar(encoded_str, vname[0]);
+					*result = true;
+				}
+			}
+			break;
+		}
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+	}
+	return current_pos;
+}
+
+/*
+ * Get current, previous and next tuples.
+ * Returns false if current row is out of partition/full frame.
+ */
+static
+bool get_slots(WindowObject winobj, int64 current_pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	TupleTableSlot *slot;
+	int		ret;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* set up current row tuple slot */
+	slot = winstate->temp_slot_1;
+	if (!window_gettupleslot(winobj, current_pos, slot))
+	{
+		elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, current_pos);
+		return false;
+
+		ret = row_is_in_frame(winstate, current_pos, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, current_pos);
+			return false;
+		}
+	}
+	econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		if (!window_gettupleslot(winobj, current_pos - 1, slot))
+		{
+			elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, current_pos - 1);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		else
+		{
+			ret = row_is_in_frame(winstate, current_pos - 1, slot);
+			if (ret <= 0)
+			{
+				elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, current_pos - 1);
+				econtext->ecxt_outertuple = winstate->null_slot;
+			}
+			else
+			{
+				econtext->ecxt_outertuple = slot;
+			}
+		}
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	if (!window_gettupleslot(winobj, current_pos + 1, slot))
+	{
+		elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, current_pos + 1);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+	{
+		ret = row_is_in_frame(winstate, current_pos + 1, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, current_pos + 1);
+			econtext->ecxt_innertuple = winstate->null_slot;
+		}
+		else
+			econtext->ecxt_innertuple = slot;
+	}
+	return true;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..e4cab36ec9 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,11 +39,19 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
 
-
 /*
  * utility routine for *_rank functions.
  */
@@ -673,7 +684,7 @@ window_last_value(PG_FUNCTION_ARGS)
 	bool		isnull;
 
 	result = WinGetFuncArgInFrame(winobj, 0,
-								  0, WINDOW_SEEK_TAIL, true,
+								  0, WINDOW_SEEK_TAIL, false,
 								  &isnull, NULL);
 	if (isnull)
 		PG_RETURN_NULL();
@@ -713,3 +724,26 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..fa100b2665 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,12 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6123', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..4fd3bd1a93 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,16 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
+
+	/* head of the reduced window frame */
+	int64		headpos_in_reduced_frame;
+	/* number of rows in the reduced window frame */
+	int64		num_rows_in_reduced_frame;
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..1e292648e9 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,15 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Wed_Jul_26_21_21_34_2023_317)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v3-0005-Row-pattern-recognition-patch-docs.patch"



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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v2 6/6] Use anonymous files to back shared memory segments
@ 2025-02-23 13:42 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-02-23 13:42 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 46 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 35a8ff92175..8864866f26c 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -105,6 +105,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -125,7 +126,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -152,9 +153,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -717,6 +718,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -734,8 +747,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -771,7 +789,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -786,7 +805,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -802,8 +821,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -822,8 +847,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -917,6 +945,8 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
 
 		/*
 		 * Fail hard if faced any issues. In theory we could try to handle this
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--q7xzg7duksj2kgko--





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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

* [PATCH v4 7/8] Use anonymous files to back shared memory segments
@ 2025-03-15 15:39 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2025-03-15 15:39 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f90cde00000-7f90d5126000 rw-s 00000000 00:01 5463 /memfd:main (deleted)
7f90d5126000-7f914de00000 ---p 00000000 00:00 0
7f914de00000-7f9175128000 rw-s 00000000 00:01 5466 /memfd:buffers (deleted)
7f9175128000-7f944de00000 ---p 00000000 00:00 0
7f944de00000-7f9455528000 rw-s 00000000 00:01 5469 /memfd:descriptors (deleted)
7f9455528000-7f94cde00000 ---p 00000000 00:00 0
7f94cde00000-7f94d5228000 rw-s 00000000 00:01 5472 /memfd:iocv (deleted)
7f94d5228000-7f954de00000 ---p 00000000 00:00 0
7f954de00000-7f9555266000 rw-s 00000000 00:01 5475 /memfd:checkpoint (deleted)
7f9555266000-7f958de00000 ---p 00000000 00:00 0
7f958de00000-7f95954aa000 rw-s 00000000 00:01 5478 /memfd:strategy (deleted)
7f95954aa000-7f95cde00000 ---p 00000000 00:00 0

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c  | 73 +++++++++++++++++++++++++++++-----
 src/backend/port/win32_shmem.c |  2 +-
 src/backend/storage/ipc/ipci.c |  2 +-
 src/include/portability/mem.h  |  2 +-
 src/include/storage/pg_shmem.h |  3 +-
 5 files changed, 68 insertions(+), 14 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index a3437973784..87000a24eea 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -107,6 +107,7 @@ typedef struct AnonymousMapping
 	Pointer shmem; 				/* Pointer to the start of the mapped memory */
 	Pointer seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -127,7 +128,7 @@ static int next_free_segment = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -150,9 +151,9 @@ static int next_free_segment = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * 7f442e010000-7f443a800000                     # reserved empty space
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * 7f444196c000-7f470a800000                     # reserved empty space
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -643,13 +644,14 @@ PGSharedMemoryAttach(IpcMemoryId shmId,
  * *hugepagesize and *mmap_flags are set to 0.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 #ifdef MAP_HUGETLB
 
 	Size		default_hugepagesize = 0;
 	Size		hugepagesize_local = 0;
 	int			mmap_flags_local = 0;
+	int			memfd_flags_local = 0;
 
 	/*
 	 * System-dependent code to find out the default huge page size.
@@ -708,6 +710,7 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	}
 
 	mmap_flags_local = MAP_HUGETLB;
+	memfd_flags_local = MFD_HUGETLB;
 
 	/*
 	 * On recent enough Linux, also include the explicit page size, if
@@ -718,7 +721,16 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 	{
 		int			shift = pg_ceil_log2_64(hugepagesize_local);
 
-		mmap_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+#endif
+
+#if defined(MFD_HUGE_MASK) && defined(MFD_HUGE_SHIFT)
+	if (hugepagesize_local != default_hugepagesize)
+	{
+		int			shift = pg_ceil_log2_64(hugepagesize_local);
+
+		memfd_flags_local |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
 	}
 #endif
 
@@ -727,6 +739,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*mmap_flags = mmap_flags_local;
 	if (hugepagesize)
 		*hugepagesize = hugepagesize_local;
+	if (memfd_flags)
+		*memfd_flags = memfd_flags_local;
 
 #else
 
@@ -734,6 +748,8 @@ GetHugePageSize(Size *hugepagesize, int *mmap_flags)
 		*hugepagesize = 0;
 	if (mmap_flags)
 		*mmap_flags = 0;
+	if (memfd_flags)
+		*memfd_flags = 0;
 
 #endif							/* MAP_HUGETLB */
 }
@@ -771,7 +787,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
-	int			mmap_flags = PG_MMAP_FLAGS;
+	int			mmap_flags = PG_MMAP_FLAGS, memfd_flags = 0;
 
 #ifndef MAP_HUGETLB
 	/* ReserveAnonymousMemory should have dealt with this case */
@@ -785,7 +801,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 		Assert(huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY);
 
 		/* Round up the request size to a suitable large value */
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, &memfd_flags);
 
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
@@ -794,6 +810,29 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	}
 #endif
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_segment),
+									   memfd_flags);
+
+	/*
+	 * Specify the segment file size using allocsize, which contains
+	 * potentially modified size.
+	 */
+	if(ftruncate(mapping->segment_fd, allocsize) == -1)
+		ereport(FATAL,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("could not truncase anonymous file for \"%s\": %m",
+						MappingName(mapping->shmem_segment))));
+
 	elog(DEBUG1, "segment[%s]: mmap(%zu) at address %p",
 		 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
@@ -807,7 +846,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 	 * a restart.
 	 */
 	ptr = mmap(base + reserved_offset, allocsize, PROT_READ | PROT_WRITE,
-			   mmap_flags | MAP_FIXED, -1, 0);
+			   mmap_flags | MAP_FIXED, mapping->segment_fd, 0);
 	mmap_errno = errno;
 
 	if (ptr == MAP_FAILED)
@@ -817,8 +856,15 @@ CreateAnonymousSegment(AnonymousMapping *mapping, Pointer base)
 					 "fallback to the non-resizable allocation",
 			 MappingName(mapping->shmem_segment), allocsize, base + reserved_offset);
 
+		/* Specify the segment file size using allocsize. */
+		if(ftruncate(mapping->segment_fd, allocsize) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(mapping->shmem_segment))));
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 	else
@@ -889,7 +935,7 @@ ReserveAnonymousMemory(Size reserve_size)
 		Size		hugepagesize, total_size = 0;
 		int			mmap_flags;
 
-		GetHugePageSize(&hugepagesize, &mmap_flags);
+		GetHugePageSize(&hugepagesize, &mmap_flags, NULL);
 
 		/*
 		 * Figure out how much memory is needed for all segments, keeping in
@@ -1070,6 +1116,13 @@ AnonymousShmemResize(void)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		if(ftruncate(m->segment_fd, new_size) == -1)
+			ereport(FATAL,
+					(errcode(ERRCODE_SYSTEM_ERROR),
+					 errmsg("could not truncase anonymous file for \"%s\": %m",
+							MappingName(m->shmem_segment))));
+
 		/* Clean up some reserved space to resize into */
 		if (munmap(m->shmem + m->shmem_size, new_size - m->shmem_size) == -1)
 			ereport(FATAL,
diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index ce719f1b412..ba972106de1 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -627,7 +627,7 @@ pgwin32_ReserveSharedMemoryRegion(HANDLE hChild)
  * use GetLargePageMinimum() instead.
  */
 void
-GetHugePageSize(Size *hugepagesize, int *mmap_flags)
+GetHugePageSize(Size *hugepagesize, int *mmap_flags, int *memfd_flags)
 {
 	if (hugepagesize)
 		*hugepagesize = 0;
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index abeb91e24fd..dc2b4becf4a 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -396,7 +396,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the number of huge pages required.
 	 */
-	GetHugePageSize(&hp_size, NULL);
+	GetHugePageSize(&hp_size, NULL, NULL);
 	if (hp_size != 0)
 	{
 		Size		hp_required;
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index ef9800732d9..40588ff6968 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 2e47b222cbb..b9573520d9a 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -124,7 +124,8 @@ extern PGShmemHeader *PGSharedMemoryCreate(Size size,
 										   PGShmemHeader **shim, Pointer base);
 extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
-extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
+extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags,
+							int *memfd_flags);
 void *ReserveAnonymousMemory(Size reserve_size);
 
 bool ProcessBarrierShmemResize(Barrier *barrier);
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0008-Support-resize-for-hugetlb.patch"



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

end of thread, other threads:[~2025-03-15 15:39 UTC | newest]

Thread overview: 319+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2023-07-26 10:49 [PATCH v3 4/7] Row pattern recognition patch (executor). Tatsuo Ishii <ishii@postgresql.org>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2024-10-15 14:18 [PATCH v1 5/5] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-02-23 13:42 [PATCH v2 6/6] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>
2025-03-15 15:39 [PATCH v4 7/8] Use anonymous files to back shared memory segments Dmitrii Dolgov <9erthalion6@gmail.com>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox